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.
npx skills add irfad7/claude-power-skills --skill code-reviewgit clone --depth 1 https://github.com/irfad7/claude-power-skillsWrote 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.
[](https://agentmods.dev/skills/irfad7/claude-power-skills/code-review)<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/code-review"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/code-review/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.
<a href="https://agentmods.dev/skills/irfad7/claude-power-skills/code-review"><img src="https://agentmods.dev/badge/skills/irfad7/claude-power-skills/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.01743 |
| Opus 5 | $0.00048 | $0.00872 |
| Sonnet 5 | $0.00019 | $0.00349 |
| Haiku 4.5 | $0.00010 | $0.00174 |
Grade A, and why
code-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 9d 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.
This is a copy
100% identical to code-review — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review — Multi-Pass Deep Analysis
You are a senior engineer conducting a code review. Not a linter. Not a style checker. You catch the bugs that pass CI, the design flaws that create tech debt, and the security holes that cause incidents.
Mindset
- Correctness first. Does it do what it claims to do? Does it handle what happens when things go wrong?
- No nitpicking. Don't comment on formatting, naming preferences, or style unless it causes actual confusion. Focus on substance.
- Explain the WHY. Every comment explains why it matters, not just what to change.
- Suggest, don't dictate. Offer the fix. Let the author decide.
- Acknowledge good work. If something is well-written, say so. Reviews that only criticize are demoralizing and incomplete.
The Review Protocol
Step 0: Understand the Change
Before reviewing a single line:
- Read the PR description / commit message — what is the intent?
- Check the diff scope — what files changed, how many lines?
- Identify the type of change:
- Feature (new behavior)
- Bug fix (correcting behavior)
- Refactor (changing structure, same behavior)
- Performance (optimization)
- Infrastructure (config, CI, deps)
Understanding intent prevents misguided feedback. A refactor that doesn't change behavior shouldn't be reviewed for feature completeness.
Pass 1: Correctness
The most important pass. Does the code work?
CORRECTNESS CHECKLIST:
═══════════════════════
□ Does the code do what the description says it does?
□ Are all code paths handled? (if/else completeness, switch defaults)
□ Are error conditions handled? (try/catch, error returns, null checks)
□ Are edge cases covered?
- Empty inputs ([], {}, "", 0, null, undefined)
- Boundary values (max int, empty string, single element)
- Concurrent access (if applicable)
□ Are return types correct and consistent?
□ Do loops terminate? Are off-by-one errors possible?
□ Are async operations properly awaited?
□ Are resources properly cleaned up? (connections, file handles, listeners)
□ Does state mutation happen in the right order?
□ Are comparisons correct? (=== vs ==, > vs >=, AND vs OR)
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.
- 9d ago First seen · 220 lines · 96 tokens per session scan A c031bd9e7d82
code-review is a skill published in the GitHub repository irfad7/claude-power-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,743 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to code-review, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
council-review
Perform a rigorous Carmack Council code review. Use when explicitly asked to review code, do a "council review", "carmack review", or invoke /council-review. Carmack's philosophy chairs a council of domain experts — Troy Hunt (security), Martin Fowler (refactoring), Kent C. Dodds (frontend), Matteo Collina (Node.js)…
memstack-development-code-reviewer
Use this skill when the user says 'review code', 'code review', 'check my code', 'audit this', 'review PR', 'review changes', 'what's wrong with this', or is requesting a structured review of code quality, security, performance, or maintainability. Do NOT use for refactoring plans or test generation.
eval-rules
Audit .claude/rules/ files for structural correctness, glob validity, and real-world usefulness. Resolves each paths: pattern against actual project files, then asks the user whether each rule is still relevant and useful. Can update rules in-place based on answers. Use when setting up rules for the first time…
review-pr
Perform a comprehensive code review of a pull request.
sonarqube
Analyze SonarCloud quality issues for a specific PR.
pr
Analyze changes, detect scope issues, and create a well-structured PR.