claude-code-action
Agents run on your own server.
Product websitegithub.com Compare with others Missing or wrong data?
- Desktop app
- No
- Browser
- Not listed
- Phone
- Not listed
- Command line
- No
- Agents
- Claude Code
- Your subscription
- Works with your own plan
- Agents run
- On your own server
- Laptop closed
- Keeps going
- Isolation
- Not listed
- Parallel agents
- Yes
- Scheduled runs
- Yes
- Coordinator agent
- No
- Built-in issues
- No
- Pull requests
- Yes
- Review screen
- Not listed
- Team
- Shared sessions
- Self-hosting
- Yes
- Licence
- MIT
- Price from
- Free
- How it charges
- No paid plan and bring your own key
- Paid plans from
- Not listed
Receipts
- Checked
- · oldest answer 2026-11-08
- Findings
- 31 published · 25 cross-checked by a second agent · read them all
- Sources
- 21 public pages on 1 site: github.com
- Screenshot
- github.com, retrieved · self captured · shows appearance, not capability
- Method
- Same rules for all 103 researched ADEs. How we check · Report wrong data
What it does
Where you use it
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
Source and scope for Where you use itAgents it runs
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
Source and scope for Agents it runsAccounts and subscriptions
Claude Pro/Max users can generate a Claude Code OAuth token using claude setup-token for the action. Direct API key, workload identity federation and supported cloud-provider authentication are documented.
Source and scope for Accounts and subscriptionsWhere agents run
The action runs on the selected user-controlled GitHub runner. GitHub event/schedule workflows execute on their runner without the initiating browser remaining open.
Source and scope for Where agents runHow work is kept apart
The action expects a Git repository at the runner workspace root.
Source and scope for How work is kept apartParallel work
Independent GitHub workflow jobs can execute this action concurrently. The action prepares a Claude run and stores execution output in each job's RUNNER_TEMP; GitHub runner and workflow concurrency limits remain external.
Source and scope for Parallel workScheduled runs
README links scheduled maintenance examples using GitHub Actions. Configured GitHub events run explicit-prompt automation without a mention. The schedule and event workflow runs on GitHub Actions, outside the initiating browser.
Source and scope for Scheduled runsGit and pull requests
Default issue mentions create a work branch; existing open PR work pushes commits to that PR branch. The action creates and pushes commits; optional signing is configurable. Default mention mode returns a prefilled GitHub PR-creation link for the human to submit. The documented default workflow refuses rebase and directs the user to do it outside the action.
Source and scope for Git and pull requestsLicence and source
The action repository code is MIT licensed.
Source and scope for Licence and sourcePrice
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
Source and scope for PriceTyped filters
Every value links to its receipt below. Read plan and surface restrictions before using a filter to decide.
| Filter | Value |
|---|---|
| Desktop OS: macOS | No |
| Desktop OS: Windows | No |
| Desktop OS: Linux | No |
| Web client | Unknown |
| Phone access: Native iOS | No |
| Phone access: Native Android | No |
| Phone access: Phone browser | Unknown |
| CLI | No |
| Coding agents: Claude Code | Yes |
| Coding agents: Codex | No |
| Coding agents: Cursor Agent | No |
| Coding agents: Gemini CLI | No |
| Coding agents: OpenCode | No |
| Coding agents: Pi | No |
| Coding agents: Grok | No |
| Coding agents: Aider | No |
| Coding agents: Antigravity | No |
| Use my subscription | Yes cross-checked |
| Where agents run: On your computer | Unknown |
| Where agents run: On your own server | Yes cross-checked |
| Where agents run: In the vendor's cloud | Unknown |
| Workspace isolation: Git worktree | Unknown |
| Workspace isolation: Container | Unknown |
| Workspace isolation: VM or microVM | Unknown |
| Parallel runs | Yes |
| Coordinator | No |
| Native issue tracking | No |
| Unattended triggers | Yes cross-checked |
| Shared prompting | Yes |
| Team roles | Unknown |
| SSO | Unknown |
| Pull request workflow | Yes cross-checked |
| Review interface | Unknown |
| Product license: Apache-2.0 | No. MIT cross-checked |
| Product license: MIT | Yes. MIT cross-checked |
| Product license: GPL-3.0 | No. MIT cross-checked |
| Product license: GPL-3.0-or-later | No. MIT cross-checked |
| Product license: AGPL-3.0 | No. MIT cross-checked |
| Product license: AGPL-3.0-or-later | No. MIT cross-checked |
| Product license: Elastic License 2.0 | No. MIT cross-checked |
| Product license: Custom terms | No. MIT cross-checked |
| Product license: Proprietary | No. MIT cross-checked |
| Self-hosting | Yes |
| Telemetry opt-out | Unknown |
| Free access | Yes cross-checked |
| Starting price: Free | Yes. Free cross-checked |
| Starting price: Up to $20/month | No. Free cross-checked |
| Starting price: $21–40/month | No. Free cross-checked |
| Starting price: $41–100/month | No. Free cross-checked |
| Starting price: Over $100/month | No. Free cross-checked |
| Starting price: Contact for pricing | No. Free cross-checked |
| Pricing model: Free, no paid plan | Yes cross-checked |
| Pricing model: Free plan | No |
| Pricing model: Subscription | No |
| Pricing model: Per seat | No |
| Pricing model: Usage-based | No |
| Pricing model: Per machine or compute | No |
| Pricing model: Bring your own key | Yes cross-checked |
| Pricing model: One-time purchase | No |
| Paid plans from: No paid plan | Unknown |
| Paid plans from: $10 or less/month | Unknown |
| Paid plans from: $11–20/month | Unknown |
| Paid plans from: $21–40/month | Unknown |
| Paid plans from: $41–100/month | Unknown |
| Paid plans from: Over $100/month | Unknown |
| Paid plans from: Contact sales | Unknown |
| Lifecycle status: Active | Unknown |
| Lifecycle status: Sunsetting | Unknown |
| Keeps going with laptop closed | Yes cross-checked |
| Open-source license | Yes. MIT cross-checked |
| Any desktop app | No |
| Paid plan up to $20/month | Unknown |
| Paid plan up to $40/month | Unknown |
| Any phone client | Unknown |
Filter receipts
Desktop OS: macOS: No
Desktop OS: macOS
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
Desktop OS: Windows: No
Desktop OS: Windows
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
Desktop OS: Linux: No
Desktop OS: Linux
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
Phone access: Native iOS: No
Phone access: Native iOS
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
Phone access: Native Android: No
Phone access: Native Android
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
CLI: No
CLI
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
Coding agents: Claude Code: Yes
Coding agents: Claude Code
Typed value: Yes.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Harnesses: The action runs Claude Code, with model/provider configuration separate.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
Coding agents: Codex: No
Coding agents: Codex
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: Cursor Agent: No
Coding agents: Cursor Agent
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: Gemini CLI: No
Coding agents: Gemini CLI
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: OpenCode: No
Coding agents: OpenCode
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: Pi: No
Coding agents: Pi
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: Grok: No
Coding agents: Grok
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: Aider: No
Coding agents: Aider
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Coding agents: Antigravity: No
Coding agents: Antigravity
Typed value: No.
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Mixed harness operation: The action and base-action run Claude Code only; there is no alternative coding-harness dispatcher in the pinned implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
Use my subscription: Yes cross-checked
Use my subscription
Typed value: Yes.
Claude Pro/Max users can generate a Claude Code OAuth token using claude setup-token for the action. Direct API key, workload identity federation and supported cloud-provider authentication are documented.
- Agent subscriptions: Claude Pro/Max users can generate a Claude Code OAuth token using claude setup-token for the action.
- Api accounts: Direct API key, workload identity federation and supported cloud-provider authentication are documented.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/setup.md
Finding: Repository admins install the app/workflow and set provider secrets; Claude Pro/Max users can generate a Claude Code OAuth token with claude setup-token.
Where agents run: On your own server: Yes cross-checked
Where agents run: On your own server
Typed value: Yes.
The action runs on the selected user-controlled GitHub runner. GitHub event/schedule workflows execute on their runner without the initiating browser remaining open.
- Byo remote: The action runs on the selected user-controlled GitHub runner.
- Client disconnect: GitHub event/schedule workflows execute on their runner without the initiating browser remaining open.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
Parallel runs: Yes
Parallel runs
Typed value: Yes.
Independent GitHub workflow jobs can execute this action concurrently. The action prepares a Claude run and stores execution output in each job's RUNNER_TEMP; GitHub runner and workflow concurrency limits remain external.
- Concurrent sessions: The per-job orchestrator has no action-wide lock or shared session store and uses job-scoped execution files.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
Coordinator: No
Coordinator
Typed value: No.
The action prepares one Claude Code run with GitHub tools. Inspection of src, base-action and the prompt builder found no action-supplied coordinator role that delegates work to separately managed agent sessions.
- Orchestration owner: Any native Claude subagent behavior belongs to the underlying harness; the action does not supply a separate coordinator/session-management protocol.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
Native issue tracking: No
Native issue tracking
Typed value: No.
The action consumes GitHub issues and pull requests; it does not own a persistent issue/task store in the pinned src and base-action implementation.
- Create: Action-owned issue creation/storage is absent; issue data is fetched through the GitHub API.
- Durable states: Durable issue states belong to GitHub, rather than a product-owned action task store.
- External tracker requirement: The issue workflow uses GitHub issue/PR context.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
Unattended triggers: Yes cross-checked
Unattended triggers
Typed value: Yes.
README links scheduled maintenance examples using GitHub Actions. Configured GitHub events run explicit-prompt automation without a mention. The schedule and event workflow runs on GitHub Actions, outside the initiating browser.
- Schedules: README links scheduled maintenance examples using GitHub Actions.
- Events: Configured GitHub events run explicit-prompt automation without a mention.
- Scheduler location: The schedule and event workflow runs on GitHub Actions, outside the initiating browser.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/custom-automations.md
Finding: Explicit prompts enable event-driven automation without mentions; tracking comments are optional. Examples cover PR review and repository updates.
Shared prompting: Yes
Shared prompting
Typed value: Yes.
Distinct GitHub users with repository write access can @claude on the same PR. Each instruction starts a new job that reads the shared PR history and operates on its head branch; an already-running job does not accept live input from other people.
- Visibility: PR participants can see the common PR comment history, agent replies and branch changes. This is shared GitHub context rather than live terminal visibility.
- Coprompting: Distinct authorized GitHub users can give successive @claude instructions on the same PR work. Each job uses the current trigger as instructions and shared prior comments as context.
- Permissions: The action checks each triggering GitHub account for repository write/admin permission, with configurable explicit exceptions.
- Shared work is the GitHub PR and its branch/history; each instruction starts a fresh action job, not a shared live terminal session.
-
Claude Code Action per-user write authorization
Finding: Each triggering GitHub actor is checked against repository write/admin access (or an explicitly configured user allowlist). Distinct authorized GitHub users can invoke the action on a shared PR.
-
Claude Code Action shared PR context
Finding: Each mention job reads the shared PR body, comments, reviews and changed files. The current trigger comment supplies instructions; previous comments remain context. Multiple authorized people can give successive instructions on the same PR work, with each instruction starting a fresh job and no live input to an already-running job.
-
Claude Code Action shared PR branch
Finding: The action checks out the existing PR head branch, so follow-up jobs from distinct GitHub users operate on the same PR work rather than separate private copies.
Pull request workflow: Yes cross-checked
Pull request workflow
Typed value: Yes.
Default issue mentions create a work branch; existing open PR work pushes commits to that PR branch. The action creates and pushes commits; optional signing is configurable. Default mention mode returns a prefilled GitHub PR-creation link for the human to submit. The documented default workflow refuses rebase and directs the user to do it outside the action.
- Commits: The action creates and pushes commits; optional signing is configurable.
- Pull requests: Default mention mode returns a prefilled GitHub PR-creation link for the human to submit.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
Product license: Apache-2.0: No. MIT cross-checked
Product license: Apache-2.0
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: MIT: Yes. MIT cross-checked
Product license: MIT
Typed value: Yes. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: GPL-3.0: No. MIT cross-checked
Product license: GPL-3.0
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: GPL-3.0-or-later: No. MIT cross-checked
Product license: GPL-3.0-or-later
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: AGPL-3.0: No. MIT cross-checked
Product license: AGPL-3.0
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: AGPL-3.0-or-later: No. MIT cross-checked
Product license: AGPL-3.0-or-later
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: Elastic License 2.0: No. MIT cross-checked
Product license: Elastic License 2.0
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: Custom terms: No. MIT cross-checked
Product license: Custom terms
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Product license: Proprietary: No. MIT cross-checked
Product license: Proprietary
Typed value: No. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Self-hosting: Yes
Self-hosting
Typed value: Yes.
The core action executes on the users own GitHub runner, still using GitHub and the chosen model provider. GitHub workflow infrastructure and the selected model provider remain dependencies.
- Self hosting: The core action executes on the users own GitHub runner, still using GitHub and the chosen model provider.
- Vendor dependencies: GitHub workflow infrastructure and the selected model provider remain dependencies.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
Free access: Yes cross-checked
Free access
Typed value: Yes.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Starting price: Free: Yes. Free cross-checked
Starting price: Free
Typed value: Yes. Free.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Starting price: Up to $20/month: No. Free cross-checked
Starting price: Up to $20/month
Typed value: No. Free.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Starting price: $21–40/month: No. Free cross-checked
Starting price: $21–40/month
Typed value: No. Free.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Starting price: $41–100/month: No. Free cross-checked
Starting price: $41–100/month
Typed value: No. Free.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Starting price: Over $100/month: No. Free cross-checked
Starting price: Over $100/month
Typed value: No. Free.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Starting price: Contact for pricing: No. Free cross-checked
Starting price: Contact for pricing
Typed value: No. Free.
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Ongoing free: The action itself is free to use under the MIT licence; no price or paid plan appears in the repository.
- Self host cost: Runs on the user's GitHub runner with no fee for the action; provider and runner costs remain separate.
- Paid only: Not paid-only: the MIT-licensed action is used from its public repository free of charge.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.
Pricing model: Free, no paid plan: Yes cross-checked
Pricing model: Free, no paid plan
Typed value: Yes.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Pricing model: Free plan: No
Pricing model: Free plan
Typed value: No.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Pricing model: Subscription: No
Pricing model: Subscription
Typed value: No.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Pricing model: Per seat: No
Pricing model: Per seat
Typed value: No.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Pricing model: Usage-based: No
Pricing model: Usage-based
Typed value: No.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Pricing model: Per machine or compute: No
Pricing model: Per machine or compute
Typed value: No.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Pricing model: Bring your own key: Yes cross-checked
Pricing model: Bring your own key
Typed value: Yes.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
claude-code-action setup guide
Finding: Credentials are an Anthropic API key or an OAuth token that Claude Pro and Max subscribers can generate.
Pricing model: One-time purchase: No
Pricing model: One-time purchase
Typed value: No.
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- Model cost: Model calls are billed by the chosen provider: Anthropic API key, Bedrock, Vertex AI, Foundry, or a Claude Pro/Max OAuth token; no amounts in these sources.
- Compute cost: It executes on the user's own GitHub runner; runner costs are not stated in these sources.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
Keeps going with laptop closed: Yes cross-checked
Keeps going with laptop closed
Typed value: Yes.
The action runs on the selected user-controlled GitHub runner. GitHub event/schedule workflows execute on their runner without the initiating browser remaining open.
- Byo remote: The action runs on the selected user-controlled GitHub runner.
- Client disconnect: GitHub event/schedule workflows execute on their runner without the initiating browser remaining open.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/custom-automations.md
Finding: Explicit prompts enable event-driven automation without mentions; tracking comments are optional. Examples cover PR review and repository updates.
Open-source license: Yes. MIT cross-checked
Open-source license
Typed value: Yes. MIT.
The action repository code is MIT licensed.
- Client license: The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
Any desktop app: No
Any desktop app
Typed value: No.
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Desktop os: The pinned repository distributes a composite action, not a native macOS, Windows or Linux desktop client.
- Mobile apps: No native iOS or Android application is distributed in this action repository.
- Cli: The action orchestrator is a runner entrypoint, not a separate product-owned user CLI. The Claude CLI it installs is the underlying harness.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
All public findings
Findings may summarize a source. They are not presented as verbatim statements.
claude-code-action:ACC-01: The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
claude-code-action:ACC-01
The product is a GitHub composite Action. Humans invoke it through GitHub issues and PRs; its code supplies no native desktop or phone client or separately distributed user-facing CLI.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action pinned source
Finding: The distribution is a composite GitHub Action that installs and runs Claude on the job runner. The repository contains action entrypoints, base-action code, GitHub MCP tools and docs, with no desktop/native-phone application or separately distributed user CLI.
claude-code-action:ACC-02: The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
claude-code-action:ACC-02
The action runs the Claude Code harness through its SDK run path. Provider configuration changes model authentication, and the custom executable input expects Claude Code; the pinned code does not implement a native route for other coding harnesses.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/usage.md
Finding: Inputs configure prompt, Claude CLI arguments, OAuth/API credentials, tool restrictions, progress tracking and validated JSON outputs.
-
Claude Code Action docs/cloud-providers.md
Finding: API execution supports Anthropic, Amazon Bedrock, Google Vertex AI and Microsoft Foundry; hosted model access is distinct from the GitHub runner.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
claude-code-action:ACC-03: Claude Pro/Max users can generate a Claude Code OAuth token using claude setup-token for the action. Direct API key, workload identity federation and supported cloud-provider authentication are documented. cross-checked
claude-code-action:ACC-03
Claude Pro/Max users can generate a Claude Code OAuth token using claude setup-token for the action. Direct API key, workload identity federation and supported cloud-provider authentication are documented.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/setup.md
Finding: Repository admins install the app/workflow and set provider secrets; Claude Pro/Max users can generate a Claude Code OAuth token with claude setup-token.
-
Claude Code Action docs/cloud-providers.md
Finding: API execution supports Anthropic, Amazon Bedrock, Google Vertex AI and Microsoft Foundry; hosted model access is distinct from the GitHub runner.
claude-code-action:ACC-04: A repository admin installs the GitHub App, stores credentials and configures the workflow. The documented workflow operates on GitHub issues, PRs and a runner checkout. Setup documents repository-admin and secret permissions. cross-checked
claude-code-action:ACC-04
A repository admin installs the GitHub App, stores credentials and configures the workflow. The documented workflow operates on GitHub issues, PRs and a runner checkout. Setup documents repository-admin and secret permissions.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/setup.md
Finding: Repository admins install the app/workflow and set provider secrets; Claude Pro/Max users can generate a Claude Code OAuth token with claude setup-token.
claude-code-action:ACC-05: The workflow accepts prompt/claude_args and emits structured JSON action outputs. GitHub App/token authorization and provider API or OAuth credentials are separate. cross-checked
claude-code-action:ACC-05
The workflow accepts prompt/claude_args and emits structured JSON action outputs. GitHub App/token authorization and provider API or OAuth credentials are separate.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/setup.md
Finding: Repository admins install the app/workflow and set provider secrets; Claude Pro/Max users can generate a Claude Code OAuth token with claude setup-token.
-
Claude Code Action docs/usage.md
Finding: Inputs configure prompt, Claude CLI arguments, OAuth/API credentials, tool restrictions, progress tracking and validated JSON outputs.
claude-code-action:ACC-06: Custom --mcp-config servers merge with built-in GitHub MCP servers; allowedTools gates enabled tools. Reading CI workflow/job logs requires actions:read and additional_permissions. The action wires GitHub tools into Claude Code and passes custom MCP configuration through Claude CLI flags. cross-checked
claude-code-action:ACC-06
Custom --mcp-config servers merge with built-in GitHub MCP servers; allowedTools gates enabled tools. Reading CI workflow/job logs requires actions:read and additional_permissions. The action wires GitHub tools into Claude Code and passes custom MCP configuration through Claude CLI flags.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/configuration.md
Finding: Custom MCP configuration extends built-in GitHub servers. CI workflow and job logs need actions:read on both the token and action configuration.
claude-code-action:PLAN-01: Issue and PR comments or an explicit workflow prompt supply task input. Mentions, issue events and configured PR events initiate action work. GitHub issues and PRs remain the external records; the action updates a tracking comment. cross-checked
claude-code-action:PLAN-01
Issue and PR comments or an explicit workflow prompt supply task input. Mentions, issue events and configured PR events initiate action work. GitHub issues and PRs remain the external records; the action updates a tracking comment.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/custom-automations.md
Finding: Explicit prompts enable event-driven automation without mentions; tracking comments are optional. Examples cover PR review and repository updates.
claude-code-action:PLAN-06: The action consumes GitHub issues and pull requests; it does not own a persistent issue/task store in the pinned src and base-action implementation.
claude-code-action:PLAN-06
The action consumes GitHub issues and pull requests; it does not own a persistent issue/task store in the pinned src and base-action implementation.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
claude-code-action:COORD-01: Independent GitHub workflow jobs can execute this action concurrently. The action prepares a Claude run and stores execution output in each job's RUNNER_TEMP; GitHub runner and workflow concurrency limits remain external.
claude-code-action:COORD-01
Independent GitHub workflow jobs can execute this action concurrently. The action prepares a Claude run and stores execution output in each job's RUNNER_TEMP; GitHub runner and workflow concurrency limits remain external.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
claude-code-action:COORD-03: The action prepares one Claude Code run with GitHub tools. Inspection of src, base-action and the prompt builder found no action-supplied coordinator role that delegates work to separately managed agent sessions.
claude-code-action:COORD-03
The action prepares one Claude Code run with GitHub tools. Inspection of src, base-action and the prompt builder found no action-supplied coordinator role that delegates work to separately managed agent sessions.
- Only the named documented or inspected parts are established; other atomic questions retain their recorded gaps.
-
Claude Code Action pinned source
Finding: The action installs Claude Code and invokes the Claude SDK run path. Its documented executable override expects a Claude Code executable; MCP tool customization does not replace the coding harness.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
claude-code-action:COORD-04: README links scheduled maintenance examples using GitHub Actions. Configured GitHub events run explicit-prompt automation without a mention. The schedule and event workflow runs on GitHub Actions, outside the initiating browser. cross-checked
claude-code-action:COORD-04
README links scheduled maintenance examples using GitHub Actions. Configured GitHub events run explicit-prompt automation without a mention. The schedule and event workflow runs on GitHub Actions, outside the initiating browser.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/custom-automations.md
Finding: Explicit prompts enable event-driven automation without mentions; tracking comments are optional. Examples cover PR review and repository updates.
claude-code-action:COORD-05: The FAQ describes using GitHub Actions logs and optional debug output for diagnostics. cross-checked
claude-code-action:COORD-05
The FAQ describes using GitHub Actions logs and optional debug output for diagnostics.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/faq.md
Finding: Default workflow creates/pushes commits but directs humans to create PRs and rebase. Destructive Git restrictions are described as system-prompt rules, not a tool-enforced security boundary.
claude-code-action:RUN-01: The action runs on the selected user-controlled GitHub runner. GitHub event/schedule workflows execute on their runner without the initiating browser remaining open. cross-checked
claude-code-action:RUN-01
The action runs on the selected user-controlled GitHub runner. GitHub event/schedule workflows execute on their runner without the initiating browser remaining open.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/custom-automations.md
Finding: Explicit prompts enable event-driven automation without mentions; tracking comments are optional. Examples cover PR review and repository updates.
claude-code-action:RUN-02: The action expects a Git repository at the runner workspace root. cross-checked
claude-code-action:RUN-02
The action expects a Git repository at the runner workspace root.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
claude-code-action:RUN-05: claude_args supports --max-turns to bound a Claude invocation. cross-checked
claude-code-action:RUN-05
claude_args supports --max-turns to bound a Claude invocation.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/usage.md
Finding: Inputs configure prompt, Claude CLI arguments, OAuth/API credentials, tool restrictions, progress tracking and validated JSON outputs.
claude-code-action:RUN-06: GitHub Actions logs expose execution diagnostics; full output may contain sensitive content. The FAQ documents permission, OIDC, tool and CI-access errors and their configuration remedies. cross-checked
claude-code-action:RUN-06
GitHub Actions logs expose execution diagnostics; full output may contain sensitive content. The FAQ documents permission, OIDC, tool and CI-access errors and their configuration remedies.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
-
Claude Code Action docs/faq.md
Finding: Default workflow creates/pushes commits but directs humans to create PRs and rebase. Destructive Git restrictions are described as system-prompt rules, not a tool-enforced security boundary.
claude-code-action:TEAM-01: Distinct GitHub users with repository write access can @claude on the same PR. Each instruction starts a new job that reads the shared PR history and operates on its head branch; an already-running job does not accept live input from other people.
claude-code-action:TEAM-01
Distinct GitHub users with repository write access can @claude on the same PR. Each instruction starts a new job that reads the shared PR history and operates on its head branch; an already-running job does not accept live input from other people.
- Shared work is the GitHub PR and its branch/history; each instruction starts a fresh action job, not a shared live terminal session.
-
Claude Code Action pinned source
Finding: Each workflow invocation prepares one Claude run and writes results to job-scoped RUNNER_TEMP. It reads GitHub issue/PR context, with no native issue database or live multi-human input channel. Separate workflow jobs have no action-wide concurrency lock.
-
Claude Code Action per-user write authorization
Finding: Each triggering GitHub actor is checked against repository write/admin access (or an explicitly configured user allowlist). Distinct authorized GitHub users can invoke the action on a shared PR.
-
Claude Code Action shared PR context
Finding: Each mention job reads the shared PR body, comments, reviews and changed files. The current trigger comment supplies instructions; previous comments remain context. Multiple authorized people can give successive instructions on the same PR work, with each instruction starting a fresh job and no live input to an already-running job.
-
Claude Code Action shared PR branch
Finding: The action checks out the existing PR head branch, so follow-up jobs from distinct GitHub users operate on the same PR work rather than separate private copies.
claude-code-action:TEAM-02: Repository write access normally gates supported actor-triggered events; documented allowed_non_write_users and bot overrides change this policy. cross-checked
claude-code-action:TEAM-02
Repository write access normally gates supported actor-triggered events; documented allowed_non_write_users and bot overrides change this policy.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
claude-code-action:TEAM-03: allowedTools/disallowedTools configure Claude tool access, and GitHub token permissions bound API operations. The FAQ describes rebase/destructive Git restrictions as system-prompt instructions, not an independent enforcement boundary. cross-checked
claude-code-action:TEAM-03
allowedTools/disallowedTools configure Claude tool access, and GitHub token permissions bound API operations. The FAQ describes rebase/destructive Git restrictions as system-prompt instructions, not an independent enforcement boundary.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/usage.md
Finding: Inputs configure prompt, Claude CLI arguments, OAuth/API credentials, tool restrictions, progress tracking and validated JSON outputs.
-
Claude Code Action docs/configuration.md
Finding: Custom MCP configuration extends built-in GitHub servers. CI workflow and job logs need actions:read on both the token and action configuration.
-
Claude Code Action docs/faq.md
Finding: Default workflow creates/pushes commits but directs humans to create PRs and rebase. Destructive Git restrictions are described as system-prompt rules, not a tool-enforced security boundary.
claude-code-action:TEAM-04: Interactive mode updates a single GitHub tracking comment with progress and final output. cross-checked
claude-code-action:TEAM-04
Interactive mode updates a single GitHub tracking comment with progress and final output.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
claude-code-action:SHIP-01: Validated JSON results become workflow action outputs. With actions:read, the action can inspect CI runs, job logs and test results. cross-checked
claude-code-action:SHIP-01
Validated JSON results become workflow action outputs. With actions:read, the action can inspect CI runs, job logs and test results.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/usage.md
Finding: Inputs configure prompt, Claude CLI arguments, OAuth/API credentials, tool restrictions, progress tracking and validated JSON outputs.
-
Claude Code Action docs/configuration.md
Finding: Custom MCP configuration extends built-in GitHub servers. CI workflow and job logs need actions:read on both the token and action configuration.
claude-code-action:SHIP-02: The action can retrieve configured CI evidence; enforcing branch protection remains a separate GitHub policy. cross-checked
claude-code-action:SHIP-02
The action can retrieve configured CI evidence; enforcing branch protection remains a separate GitHub policy.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/configuration.md
Finding: Custom MCP configuration extends built-in GitHub servers. CI workflow and job logs need actions:read on both the token and action configuration.
claude-code-action:SHIP-03: Default issue mentions create a work branch; existing open PR work pushes commits to that PR branch. The action creates and pushes commits; optional signing is configurable. Default mention mode returns a prefilled GitHub PR-creation link for the human to submit. The documented default workflow refuses rebase and directs the user to do it outside the action. cross-checked
claude-code-action:SHIP-03
Default issue mentions create a work branch; existing open PR work pushes commits to that PR branch. The action creates and pushes commits; optional signing is configurable. Default mention mode returns a prefilled GitHub PR-creation link for the human to submit. The documented default workflow refuses rebase and directs the user to do it outside the action.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
-
Claude Code Action docs/faq.md
Finding: Default workflow creates/pushes commits but directs humans to create PRs and rebase. Destructive Git restrictions are described as system-prompt rules, not a tool-enforced security boundary.
claude-code-action:SHIP-04: The default action documentation says it does not merge branches; this is described as a prompt restriction. cross-checked
claude-code-action:SHIP-04
The default action documentation says it does not merge branches; this is described as a prompt restriction.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/faq.md
Finding: Default workflow creates/pushes commits but directs humans to create PRs and rebase. Destructive Git restrictions are described as system-prompt rules, not a tool-enforced security boundary.
claude-code-action:SHIP-05: The default result includes a human PR-creation link, distinct from evidence that a PR was created. cross-checked
claude-code-action:SHIP-05
The default result includes a human PR-creation link, distinct from evidence that a PR was created.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
claude-code-action:OWN-01: The action repository code is MIT licensed. cross-checked
claude-code-action:OWN-01
The action repository code is MIT licensed.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: The action repository is MIT licensed.
claude-code-action:OWN-02: The core action executes on the users own GitHub runner, still using GitHub and the chosen model provider. GitHub workflow infrastructure and the selected model provider remain dependencies. cross-checked
claude-code-action:OWN-02
The core action executes on the users own GitHub runner, still using GitHub and the chosen model provider. GitHub workflow infrastructure and the selected model provider remain dependencies.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: GitHub Action runs Claude Code on the selected GitHub runner, processes PRs/issues, updates tracking comments and exposes structured outputs.
-
Claude Code Action docs/cloud-providers.md
Finding: API execution supports Anthropic, Amazon Bedrock, Google Vertex AI and Microsoft Foundry; hosted model access is distinct from the GitHub runner.
claude-code-action:OWN-03: Full debug output may include sensitive context, tokens and tool content and requires access restrictions. cross-checked
claude-code-action:OWN-03
Full debug output may include sensitive context, tokens and tool content and requires access restrictions.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Claude Code Action docs/security.md
Finding: Write-access checks gate supported actor-driven events, with explicit opt-in exceptions. Default mentions push a branch and return a prefilled PR link. Full debug output can expose private data.
claude-code-action:OWN-04: The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner. cross-checked
claude-code-action:OWN-04
The action itself is free (MIT) with no separate price; Claude usage is paid via the user's Anthropic API key, cloud provider (Bedrock/Vertex/Foundry) or Claude Pro/Max subscription, and it runs on the user's own GitHub runner.
- First-party pricing pages, terms and licences read 2026-11-10; no purchase, billing or authenticated account test.
-
Finding: The action runs on the user's own GitHub runner and authenticates to Anthropic API, Amazon Bedrock, Google Vertex AI or Microsoft Foundry, so model calls are billed by the chosen provider.
-
claude-code-action setup guide
Finding: Credentials are an Anthropic API key or an OAuth token that Claude Pro and Max subscribers can generate.
-
Finding: The MIT license grants permission to use, copy, modify and distribute the software free of charge.
claude-code-action:OWN-06: The latest retrieved version is v1.0.269 dated 2026-11-06. cross-checked
claude-code-action:OWN-06
The latest retrieved version is v1.0.269 dated 2026-11-06.
- Only the cited atomic findings are established. Remaining atomic requirements and the full rubric scenario remain unverified.
-
Finding: Public release v1.0.269 was published 2026-11-06.
claude-code-action:OWN-08: The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's. cross-checked
claude-code-action:OWN-08
The action is MIT-licensed open source used from its public repository at no charge, with no paid plan shown. Model usage is paid to Anthropic or the chosen cloud provider, and runner costs are GitHub's.
- Provider free tiers, GitHub Actions minute costs and card requirements were not checked. No workflow was run.
-
Finding: MIT License, copyright Anthropic, PBC, granting permission free of charge to use, copy, modify and distribute the software.
-
Claude Code Action README: Quickstart and License
Finding: Setup installs the GitHub app and secrets from Claude Code with /install-github-app or manually; the README names provider credentials but no price or paid plan for the action, and states the MIT licence.