Plans Dir Exists + Claude Collector

✓ Guardrail ↓ Collector Experimental Devex Build And Ci

Enforce Plans Dir Exists using data collected by Claude Collector. Automatically check devex build and ci standards on every PR.

Guardrail: Verifies that a dedicated plans directory exists for AI agent task planning. A dedicated directory keeps AI-generated plans organized and reviewable.

Data Source: 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.

Get Started View on GitHub

How Claude Collector Powers This Guardrail

The Claude Collector gathers metadata from your systems. This data flows into Lunar's Component JSON, where the Plans Dir Exists guardrail evaluates it against your standards.

When enabled, this check runs automatically on every PR and in AI coding workflows, providing real-time enforcement with actionable feedback.

↓ Claude Collector Gathers Data Collector

Extracts metadata from code, configs, and tool outputs

{ } Component JSON

Data centralized in structured format for evaluation

✓ Plans Dir Exists Checks Guardrail

Pass/fail result with actionable feedback in PRs

Quick Start Configuration

Add both the collector and policy to your lunar-config.yml to enable this guardrail.

📄 lunar-config.yml

# Step 1: Enable the Claude Collector
collectors:
  - uses: github://earthly/lunar-lib/collectors/claude@v1.0.5
    # with: ...

# Step 2: Enable the AI Guardrails
policies:
  - uses: github://earthly/lunar-lib/policies/ai@v1.0.5
    include: [plans-dir-exists]
    # with: ...

What Claude Collector Collects

This collector gathers the following data that the Plans Dir Exists guardrail evaluates.

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[].

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.

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).

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.

View all 5 collectors in Claude Collector →

Example Data Flow

Here's an example of the data that Claude Collector writes to the Component JSON, which Plans Dir Exists then evaluates.

{ } component.json From Claude Collector

{
  "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 Options

Claude Collector 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

AI Guardrails Inputs

Input	Required	Default	Description
`canonical_filename`	Optional	`AGENTS.md`	The canonical (vendor-neutral) instruction filename
`min_lines`	Optional	`10`	Minimum number of lines for the root instruction file (0 to disable)
`max_lines`	Optional	`300`	Maximum number of lines for the root instruction file (0 to disable)
`max_total_bytes`	Optional	`32768`	Maximum combined bytes across all instruction files (0 to disable)
`required_sections`	Optional	`Project Overview,Build Commands`	Comma-separated required section heading substrings (case-insensitive)
`min_annotation_percentage`	Optional	`0`	Minimum percentage of commits that should have AI annotations (0 = awareness mode)

Learn More

Guardrail · AI Guardrails Plans Dir Exists View all compatible integrations

→

Collector Claude Collector View full documentation

→

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

Plans Dir Exists + Claude Collector

How Claude Collector Powers This Guardrail

Quick Start Configuration

What Claude Collector Collects

code-reviewer

run-code-review

cicd

instruction-file

Example Data Flow

Configuration Options

Claude Collector Inputs

AI Guardrails Inputs

Other Guardrails Using Claude Collector

Learn More

Ready to Automate Your Standards?

`code-reviewer`

`run-code-review`

`cicd`

`instruction-file`