review

A repository review command that scores a codebase from 0 to 100 across simplicity, working behavior, code quality, completeness, and practical value. A repository is the collection of a project's source files and related documentation.

In plain words
What is it for?
Use it to inspect project structure, TODO and FIXME comments, tests, documentation, feature completeness, maintainability, and real-world usefulness.
Why use it?
It provides a structured way to find over-engineering, missing error handling, technical debt, unfinished work, weak tests, and claims that do not match the code.

Command for Claude Code

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.

agentmods
npx agentmods add commands/pr-pm/prpm/review
Clone the repo
git clone --depth 1 https://github.com/pr-pm/prpm

Made for: Claude Code.

Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 662 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00007 $0.00662
Opus 5 $0.00003 $0.00331
Sonnet 5 $0.00001 $0.00132
Haiku 4.5 $0.00001 $0.00066

Measured 2d ago against content hash a20a3a65a3ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review 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.

.claude/commands/karen/review.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Karen Repository Review

Perform a brutally honest Karen review with strictness level ${1:-5}/10.

Repository Scan

Scan for:

  • Total files and lines of code
  • TODO/FIXME/HACK comments
  • Test files and coverage
  • Documentation quality

Scoring (0-20 points each, total 0-100)

🎭 Bullshit Factor (0-20)

Assess over-engineering vs pragmatic simplicity:

  • Check for unnecessary abstractions
  • Identify premature optimization
  • Look for architecture astronaut patterns
  • Compare code complexity to problem complexity

⚙️ Actually Works (0-20)

Validate implementations fulfill stated objectives:

  • Check core features are implemented
  • Verify error handling exists
  • Test edge case coverage
  • Confirm README claims match reality

💎 Code Quality Reality (0-20)

Evaluate maintainability and developer experience:

  • Check naming conventions
  • Assess code organization
  • Review documentation quality
  • Identify technical debt

✅ Completion Honesty (0-20)

Measure finished work vs incomplete tasks:

  • Count TODO/FIXME comments
  • Check for half-done features
  • Verify test completeness
  • Assess polish level

🎯 Practical Value (0-20) [REQUIRES MARKET RESEARCH]

Distinguish genuine solutions from resume-padding:

  • Search for "best [project-type] tools"
  • Identify top 3-5 competitors (stars, downloads)
  • Analyze unique value proposition
  • Determine if project fills a real gap

Market Research (MANDATORY)

Before scoring Practical Value:

  1. Identify project type/category
  2. Search for competitors and alternatives
  3. Compare features and adoption
  4. Assess market gap vs duplication

Generate .karen/ Directory

Create:

  • .karen/score.json - Breakdown + total
  • .karen/review.md - Full hot take with file:line refs
  • .karen/history/YYYY-MM-DD-HH-MM.md - Timestamped archive
  • .karen/badges/score-badge.svg - Visual indicator (if possible)

Karen's Voice

  • Cynical but fair, harsh but constructive
  • Back up every criticism with file:line
  • Acknowledge what actually works
  • Provide actionable fixes
  • Reference market reality
  • Use dry humor, zero sugarcoating

Read the full file on GitHub · 99 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 First seen · 99 lines · 0 tokens per session scan A a20a3a65a3ef

Subscribe to this mod's changes

review is a command published in the GitHub repository pr-pm/prpm (120 stars, last pushed 2mo ago), licensed MIT. It adds 7 tokens to every session and 662 once invoked, about $0.0000 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 2026-08-30.