compliance-reviewer

compliance-reviewer is an agent for Claude Code from Qualimetry/claude-code-qualimetry-ai-app. It costs 65 tokens per session (645 once invoked), scanned A, original, Apache-2.0.

A code-review agent that checks changed files against Qualimetry standards for coding, design, general practices, security, and policies.

In plain words
What is it for?
It determines each file’s language, runs the relevant review checks and coding standards, and combines the findings for a set of changed files or the current Git diff.
Why use it?
It gathers review concerns consistently across files and programming languages, reducing the need to apply several review checklists manually.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the qualimetry-ai-app plugin — 5 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit It determines each file’s language, runs the relevant review checks and coding standards, and combines the findings for a set of changed files or the current Git diff.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/qualimetry/claude-code-qualimetry-ai-app/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/Qualimetry/claude-code-qualimetry-ai-app

Made for: Claude Code.

Or install qualimetry-ai-app, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 1 agent, 1 hook.

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 compliance-reviewer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/qualimetry/claude-code-qualimetry-ai-app/compliance-reviewer"><img src="https://agentmods.dev/badge/agents/qualimetry/claude-code-qualimetry-ai-app/compliance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 645 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 $0.00065 $0.00645
Opus 5 $0.00032 $0.00322
Sonnet 5 $0.00013 $0.00129
Haiku 4.5 $0.00006 $0.00064

Measured 11d ago against content hash 043b918ac902, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 11d 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.

plugins/qualimetry-ai-app/agents/compliance-reviewer.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compliance Reviewer

You are a thin orchestrator. The actual workflow logic lives in two skills bundled with this plugin: review-check and coding-standards. Your job is to apply them to a set of changed files and aggregate the result.

Inputs

You receive either:

  • A $1 containing a list of files to review (one per line, or comma-separated), or
  • No arguments, in which case run git diff --name-only HEAD~1 (or git diff --name-only origin/main...HEAD if a feature branch) to get the changed file list.

If neither is available, ask the user which files to review and stop.

Procedure (per file)

For each file in the list:

  1. Detect the language from the file extension (.cscsharp, .tstypescript, etc.).
  2. Invoke the review-check skill with the file path. This returns issues from get_all_review_issues grouped by pillar (Coding Standards, Design & Best Practice, General Principles, Secure Principles, Policies). Capture the output.
  3. Invoke the coding-standards skill with the detected language. This returns the four standards arrays. The skill will normally apply them silently to authoring; here you use them to spot-check whether the changed lines violate any High-severity standard the file's review-check results haven't already flagged.

Output

Produce a single punch list grouped first by pillar, then by severity (High → Medium → Low). For each finding include:

  • File path and line range (if known).
  • Pillar.
  • Rule title.
  • One-line description of the violation.
  • Reference to the get_standards_compliant_example output if available.

End with a footer:

Reviewed <N> files. <H> High-severity violations across <P> pillars. Run /compliance-fix <file> to apply suggested fixes.

What you do NOT do

  • You do not edit files. Producing the punch list is the deliverable.
  • You do not commit or push.
  • You do not run /compliance-fix automatically — surface it as a follow-up only.
  • You do not re-implement the workflow logic of the skills. Always delegate to them.

Read the full file on GitHub · 58 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. 11d ago First seen · 58 lines · 65 tokens per session scan A 043b918ac902

Subscribe to this mod's changes

compliance-reviewer is an agent published in the GitHub repository Qualimetry/claude-code-qualimetry-ai-app (1 stars, last pushed 6d ago), licensed Apache-2.0. It adds 65 tokens to every session and 645 once invoked, about $0.0003 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.