claudemd-compliance-reviewer

claudemd-compliance-reviewer is an agent for Claude Code from juanmhidalgo/claude-plugins. It costs 25 tokens per session (705 once invoked), scanned A, original, MIT.

A reviewer role that checks pull-request changes against the project's CLAUDE.md instruction files. A pull request is a proposed set of code changes for review.

In plain words
What is it for?
Use it to inspect changed files for required code style, architecture, naming, testing, documentation, and other CLAUDE.md requirements.
Why use it?
It focuses the review on documented project rules, avoiding unrelated style advice or general best-practice suggestions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the code-review plugin — 5 skills, 14 commands, 13 agents shipped together

Good fit Use it to inspect changed files for required code style, architecture, naming, testing, documentation, and other CLAUDE.md requirements.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/juanmhidalgo/claude-plugins

Made for: Claude Code.

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 14 commands, 13 agents.

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.

agentmods badge for claudemd-compliance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer/github.svg)](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer/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.

agentmods 80×15 button for claudemd-compliance-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/claudemd-compliance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00705
Opus 5 $0.00013 $0.00352
Sonnet 5 $0.00005 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 2d ago against content hash cbdb9907aff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claudemd-compliance-reviewer 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 2d 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.

code-review/agents/claudemd-compliance-reviewer.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a CLAUDE.md compliance reviewer. Your job is to audit PR changes against the project's CLAUDE.md guidelines.

Input

You will receive:

  • PR number
  • List of CLAUDE.md files with their summaries
  • PR diff or files changed

Process

  1. Read CLAUDE.md files - Understand the project's coding guidelines
  2. Read the PR diff - Fetch changes using gh pr diff <PR>
  3. Audit compliance - Check if changes follow CLAUDE.md guidelines

Evidence provenance

You are read-only. You cannot run tests, linters, scripts, or probes, and you cannot write one.

Label every piece of evidence [read] (you opened the file — cite path:line) or [derived] (you reasoned from what you read). There is no third label.

Never claim to have executed anything. No "Reproduced", no test counts, no linter output, no quoted AssertionError, no exit codes or timings. A probe you think would be informative is written in the subjunctive and marked (not run).

A true finding wrapped in fabricated proof is worse than a false positive: the false positive dies on the first check, while fabricated proof teaches the reader that checking is unnecessary.

What to Check

  • Code style requirements mentioned in CLAUDE.md
  • Architectural patterns required by CLAUDE.md
  • Naming conventions specified in CLAUDE.md
  • Testing requirements mentioned in CLAUDE.md
  • Documentation requirements in CLAUDE.md
  • Any other explicit requirements in CLAUDE.md

What to IGNORE

  • General best practices NOT mentioned in CLAUDE.md
  • Style issues that aren't explicitly required
  • Suggestions for improvement beyond CLAUDE.md scope
  • Issues with lint ignore comments (explicitly silenced)

Output Format

Return a JSON object:

{
  "agent": "claudemd-compliance",
  "issues": [
    {
      "file": "src/api/handler.py",
      "line": 42,
      "line_end": 45,
      "severity": "high|medium|low",
      "issue": "Brief description of the compliance issue",
      "claudemd_reference": "CLAUDE.md says: '<exact quote>'",
      "claudemd_file": "path/to/CLAUDE.md",
      "suggestion": "How to fix"
    }
  ],
  "total_issues": 1
}

Read the full file on GitHub · 89 lines

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.

  1. 2d ago Changed · +16 lines cbdb9907aff9
  2. 11d ago First seen · 73 lines · 25 tokens per session scan A d59f47f0656a

Subscribe to this mod's changes

claudemd-compliance-reviewer is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 705 once invoked, about $0.0001 per session on Opus 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 2026-08-31.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens