What is claude-code-base-action CLAUDE.md?

A project guide for a GitHub Action that runs Claude Code inside GitHub workflows. GitHub Actions are automated jobs that run in response to events such as code pushes or pull requests.

Use it when developing or testing the action, preparing prompts, checking its JSON execution logs, or configuring which supported AI provider it uses.

It explains how to install dependencies, format and type-check the action, run its tests, and authenticate with Anthropic, AWS Bedrock, or Google Vertex AI.

How anthropics/claude-code-base-action configures Claude Code

About the project

Claude Code Base Action is a GitHub Action that installs and runs Claude Code inside GitHub Actions workflows. Developers use it to build custom automation around Claude Code, while the calling workflow remains responsible for deciding which project files and inputs are trusted. The catalogue MCP and instruction support using this action.

anthropics/claude-code-base-action · 1,032 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to anthropics/claude-code-base-action. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/anthropics/claude-code-base-action/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/anthropics/claude-code-base-action

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anthropics/claude-code-base-action/claude-md/github.svg)](https://agentmods.dev/instructions/anthropics/claude-code-base-action/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/anthropics/claude-code-base-action/claude-md"><img src="https://agentmods.dev/badge/instructions/anthropics/claude-code-base-action/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/anthropics/claude-code-base-action/claude-md"><img src="https://agentmods.dev/badge/instructions/anthropics/claude-code-base-action/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 404 This file is loaded in full into every session.

When invoked 404 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00404	$0.00404
Opus 5.5	$0.00162	$0.00162
Sonnet 5.5	$0.00081	$0.00081
Haiku 4.5	$0.00040	$0.00040

Measured 2mo ago against content hash ce9cf4cb97bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-code-base-action CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 59 lines

What it actually says

CLAUDE.md

Common Commands

Development Commands

Build/Type check: bun run typecheck
Format code: bun run format
Check formatting: bun run format:check
Run tests: bun test
Install dependencies: bun install

Action Testing

Test action locally: ./test-local.sh
Test specific file: bun test test/prepare-prompt.test.ts

Architecture Overview

This is a GitHub Action that allows running Claude Code within GitHub workflows. The action consists of:

Core Components

Action Definition (action.yml): Defines inputs, outputs, and the composite action steps
Prompt Preparation (src/index.ts): Runs Claude Code with specified arguments

Key Design Patterns

Uses Bun runtime for development and execution
JSON streaming output format for execution logs
Composite action pattern to orchestrate multiple steps
Provider-agnostic design supporting Anthropic API, AWS Bedrock, and Google Vertex AI

Provider Authentication

Anthropic API (default): Requires API key via anthropic_api_key input
AWS Bedrock: Uses OIDC authentication when use_bedrock: true
Google Vertex AI: Uses OIDC authentication when use_vertex: true

Testing Strategy

Local Testing

Use act tool to run GitHub Actions workflows locally
test-local.sh script automates local testing setup
Requires ANTHROPIC_API_KEY environment variable

Test Structure

Unit tests for configuration logic
Integration tests for prompt preparation
Full workflow tests in .github/workflows/test-base-action.yml

Important Technical Details

Outputs execution logs as JSON to /tmp/claude-execution-output.json
Timeout enforcement via timeout command wrapper
Strict TypeScript configuration with Bun-specific settings

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 59 lines · 404 tokens per session scan A ce9cf4cb97bf

Subscribe to this mod's changes

claude-code-base-action CLAUDE.md is an instructions file published in the GitHub repository anthropics/claude-code-base-action (1,032 stars, last pushed 3d ago), licensed MIT. It adds 404 tokens to every session, about $0.0016 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

claude-code-base-action CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-code-base-action CLAUDE.mdanthropics/claude-code-base-action	Instructions file	1.0k	3d ago	MIT	A	404	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

claude-code-base-action: Instructions file for Claude Code