Claude Collector

↓ Collector Experimental Code Analysis

Detects Claude Code Review on pull requests, captures Claude CLI invocations in CI, discovers CLAUDE.md instruction files, and runs custom Claude prompts against code. Writes to normalized ai.code_reviewers[] plus Claude-specific data in ai.native.claude.

Add claude to your lunar-config.yml:

uses: github://earthly/lunar-lib/collectors/claude@v1.0.5

Get Started View on GitHub

What This Integration Collects

This integration includes 5 collectors that gather metadata from your systems.

Collector code

`code-reviewer`

Detects Claude Code Review check-runs on pull requests by querying the GitHub check-runs API. Waits for scan completion and writes a normalized entry to ai.code_reviewers[].

claude code review ai review pull request

Book a demo

Collector code

`run-code-review`

Runs the Claude CLI in review mode against pull request diffs. Captures review findings, severity levels, and affected files. Writes results to ai.native.claude.code_review for Claude-specific policy evaluation.

claude code review ai review pull request claude cli

Book a demo

Collector ci-after-command

`cicd`

Detects Claude Code CLI invocations in CI pipelines. Records the command string, version, and extracted flags (--allowedTools, --disallowedTools, --mcp-config) for policy-level analysis. Also appends to ai.code_reviewers[] when it detects review-mode invocations (e.g. claude --review).

claude claude code ai ci ci safety

Book a demo

Collector code

`instruction-file`

Discovers CLAUDE.md instruction files across the repository. Records file path, line count, byte size, and whether it is a symlink to AGENTS.md. Writes to ai.native.claude.instruction_file and appends to ai.instructions.all[] for normalized cross-tool access.

claude.md instruction file agent context

Book a demo

Collector code

`run-prompt`

Runs a Claude AI prompt against the repository and collects the results. Supports optional JSON schema enforcement for structured output. Use cases include feature flag detection, documentation quality analysis, and architecture pattern detection.

claude ai llm code analysis pattern detection anthropic

Book a demo

How Collectors Fit into Lunar

Lunar watches your code and CI/CD systems to collect SDLC data from config files, test results, IaC, deployment configurations, security scans, and more.

Collectors are the automatic data-gathering layer. They extract structured metadata from your repositories and pipelines, feeding it into Lunar's centralized database where guardrails evaluate it to enforce your engineering standards.

Learn How Lunar Works →

↓ Collectors Gather Data This Integration

Triggered by code changes or CI pipelines, collectors extract metadata from config files, tool outputs, test results, and scans

{ } Centralized as JSON

All data merged into each component's unified metadata document

✓ Guardrails Enforce Standards

Real-time feedback in PRs and AI workflows

Example Collected Data

This collector writes structured metadata to the Component JSON. Here's an example of the data it produces:

{ } component.json Component JSON

{
  "ai": {
    "code_reviewers": [
      {
        "tool": "claude",
        "check_name": "Claude Code Review",
        "detected": true,
        "last_seen": "2024-01-14T08:00:00Z"
      }
    ],
    "instructions": {
      "all": [
        {
          "path": "CLAUDE.md",
          "dir": ".",
          "filename": "CLAUDE.md",
          "lines": 85,
          "bytes": 3200,
          "is_symlink": true,
          "symlink_target": "AGENTS.md"
        }
      ]
    },
    "native": {
      "claude": {
        "instruction_file": {
          "exists": true,
          "path": "CLAUDE.md",
          "lines": 85,
          "bytes": 3200,
          "is_symlink": true,
          "symlink_target": "AGENTS.md"
        },
        "cicd": {
          "cmds": [
            {
              "cmd": "claude -p --output-format json --allowedTools Bash(git*) Read 'review this PR'",
              "tool": "claude",
              "version": "1.0.20",
              "allowed_tools": "Bash(git*) Read"
            }
          ]
        },
        "code_review": {
          "ran": true,
          "findings_count": 3,
          "findings": [
            {
              "severity": "warning",
              "file": "src/auth.ts",
              "line": 42,
              "message": "Token expiry not checked before use"
            }
          ]
        }
      }
    }
  }
}

Configuration

Configure this collector in your lunar-config.yml.

Inputs

Input	Required	Default	Description
`path`	Required	—	JSON component path for run-prompt results (e.g., ".code_patterns.feature_flags")
`prompt`	Required	—	Prompt for Claude to run on the component repository (run-prompt only)
`json_schema`	Required	—	Optional JSON schema for structured output in run-prompt

Secrets

This collector requires the following secrets to be configured in Lunar:

Secret	Description
`GH_TOKEN`	GitHub token for API access (required for code-reviewer check-runs query)
`ANTHROPIC_API_KEY`	Anthropic API key for Claude authentication (required for run-prompt and run-code-review)

Documentation

View on GitHub

Claude Collector

Detect Claude code review activity, CI usage, instruction files, and run AI prompts against repository code.

Overview

This collector detects Claude Code Review on pull requests, captures Claude CLI invocations in CI pipelines, discovers CLAUDE.md instruction files, and can run custom Claude AI prompts or code review against PRs.

Code reviewer data writes to normalized ai.code_reviewers[]; instruction files write to both ai.native.claude.instruction_file and ai.instructions.all[] via array append. CI data writes to ai.native.claude.cicd, run-code-review to ai.native.claude.code_review, and run-prompt to a user-configurable path.

Collected Data

This collector writes to the following Component JSON paths:

Path	Type	Description
`.ai.code_reviewers[]`	array append	Claude Code Review detection entry with check name and timestamp
`.ai.instructions.all[]`	array append	CLAUDE.md entry appended to the normalized instruction files array
`.ai.native.claude.instruction_file`	object	CLAUDE.md file: existence, path, line count, byte size, symlink status
`.ai.native.claude.cicd.cmds[]`	array	Claude CLI invocations in CI: command string, version, allowed/disallowed tools, MCP config
`.ai.native.claude.code_review`	object	Claude CLI review mode results: findings count, severity, affected files
`{path}` (configurable)	any	Claude prompt response from run-prompt, optionally conforming to a JSON schema

Collectors

This integration provides the following collectors:

Collector	Hook	Description
`code-reviewer`	`code` (PRs only)	Detects Claude Code Review check-runs on pull requests
`run-code-review`	`code` (PRs only)	Runs Claude CLI in review mode against PR diffs
`instruction-file`	`code`	Discovers CLAUDE.md instruction files with metadata and symlink status
`cicd`	`ci-after-command` (binary: claude)	Captures Claude CLI invocations in CI with flag extraction
`run-prompt`	`code`	Runs a Claude AI prompt against the repo and collects structured results

Installation

Code Review Detection

collectors:
  - uses: github://earthly/lunar-lib/collectors/claude@main
    on: ["domain:your-domain"]
    include: [code-reviewer]
    secrets:
      GH_TOKEN: "${{ secrets.GH_TOKEN }}"

Run Code Review (AI-Powered)

collectors:
  - uses: github://earthly/lunar-lib/collectors/claude@main
    on: ["domain:your-domain"]
    include: [run-code-review]
    secrets:
      ANTHROPIC_API_KEY: "${{ secrets.ANTHROPIC_API_KEY }}"
      GH_TOKEN: "${{ secrets.GH_TOKEN }}"

CI Detection + Instruction Files

collectors:
  - uses: github://earthly/lunar-lib/collectors/claude@main
    on: ["domain:your-domain"]

Run Prompt (AI-Powered Analysis)

collectors:
  - uses: github://earthly/lunar-lib/collectors/claude@main
    on: ["domain:your-domain"]
    include: [run-prompt]
    with:
      path: ".code_patterns.feature_flags"
      prompt: "Find all feature flags in this repository and return them as a list"
    secrets:
      ANTHROPIC_API_KEY: "${{ secrets.ANTHROPIC_API_KEY }}"

With JSON Schema Enforcement

collectors:
  - uses: github://earthly/lunar-lib/collectors/claude@main
    on: [backend]
    include: [run-prompt]
    with:
      path: ".code_patterns.lifecycle"
      prompt: "Analyze this codebase for graceful shutdown handling."
      json_schema: |
        {
          "type": "object",
          "properties": {
            "handles_sigterm": {"type": "boolean"},
            "shutdown_timeout_seconds": {"type": "number"},
            "files": {"type": "array", "items": {"type": "string"}}
          }
        }
    secrets:
      ANTHROPIC_API_KEY: "${{ secrets.ANTHROPIC_API_KEY }}"

Open Source

This collector is open source and available on GitHub. Contribute improvements, report issues, or fork it for your own use.

View Repository

Common Use Cases

Explore guardrails that use data from Claude Collector.

Code Reviewer + Claude Collector Verifies that at least one AI code reviewer is active on the component. Checks...

→

Instruction File Exists + Claude Collector Verifies that an agent instruction file exists at the repository root....

→

Canonical Naming + Claude Collector Verifies the root instruction file uses the canonical vendor-neutral name...

→

Instruction File Length + Claude Collector Validates that the root instruction file is within reasonable length bounds. Too...

→

Instruction File Sections + Claude Collector Ensures the root instruction file contains required section headings. Validates...

→

Plans Dir Exists + Claude Collector Verifies that a dedicated plans directory exists for AI agent task planning. A...

→

Ai Authorship Annotated + Claude Collector Verifies that commits include AI authorship annotations. Supports the Git AI...

→

Cli Safe Flags + Claude Collector Ensures Claude CLI invocations in CI do not use dangerous...

→

Cli Structured Output + Claude Collector Ensures Claude CLI invocations in CI headless mode use structured JSON...

→

Symlinked Aliases + Claude Collector Verifies that CLAUDE.md exists as a symlink to AGENTS.md. Claude Code does...

→

Ready to Automate Your Standards?

See how Lunar can turn your AGENTS.md, engineering wiki, compliance docs, or postmortem action items into automated guardrails with our 100+ built-in guardrails.

Works with any process

AI agent rules & prompt files

Post-mortem action items

Security & compliance policies

Testing & quality requirements

Automate Now

Paste your AGENTS.md or manual process doc and get guardrails in minutes

Book a Demo

Claude Collector

What This Integration Collects

code-reviewer

run-code-review

cicd

instruction-file

run-prompt

How Collectors Fit into Lunar

Example Collected Data

Configuration

Inputs

Secrets

Related

Documentation

Claude Collector

Overview

Collected Data

Collectors

Installation

Code Review Detection

Run Code Review (AI-Powered)

CI Detection + Instruction Files

Run Prompt (AI-Powered Analysis)

With JSON Schema Enforcement

Open Source

Common Use Cases

Ready to Automate Your Standards?

`code-reviewer`

`run-code-review`

`cicd`

`instruction-file`

`run-prompt`