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.
git clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-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/commands/huuanh20/awesome-ai-agent-skills/code-review)<a href="https://agentmods.dev/commands/huuanh20/awesome-ai-agent-skills/code-review"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-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/commands/huuanh20/awesome-ai-agent-skills/code-review"><img src="https://agentmods.dev/badge/commands/huuanh20/awesome-ai-agent-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 | $0.00022 | $0.01022 |
| Opus 5 | $0.00011 | $0.00511 |
| Sonnet 5 | $0.00004 | $0.00204 |
| Haiku 4.5 | $0.00002 | $0.00102 |
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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ck:code-review
Input: $ARGUMENTS
Mode Selection
If $ARGUMENTS contains a PR number, PR URL, or --pr → PR Review Mode.
Otherwise → Local Review Mode.
Local Review Mode
Phase 1 — GATHER
git diff --name-only HEAD
If no changed files, stop: "Nothing to review."
Read CLAUDE.md (if present) for project conventions.
Read each changed file in full.
For planned work, locate the phase's ck:quality receipt and latest ck:test report. Verify the receipt before reviewing. A missing/stale quality receipt or missing required test report is a readiness finding, not something this command silently recreates.
Phase 2 — REVIEW
Spawn the code-reviewer agent with:
- Full file contents of each changed file
- CLAUDE.md contents (if present)
- Recent context:
git log --oneline -5
Phase 3 — VALIDATE ARTIFACTS
If current ck:test and build artifacts exist, validate their commands, timestamps, scope, and verdicts. Do not rewrite tests or duplicate ck:test. For a standalone repository with no ck artifacts, detect the stack and run the project's documented build/test commands as fallback:
# .NET
dotnet build --no-restore -q && dotnet test
# Node / TypeScript
npm run build && npm test
# Python
python -m pytest
# Or use task runner if present (Makefile, Taskfile, package.json scripts)
Report pass/fail for build and tests separately.
Phase 4 — REPORT
Present the agent's findings plus build/test results:
---
## Review Summary
| Severity | Count |
|----------|-------|
| CRITICAL | 0 |
| HIGH | 1 |
| MEDIUM | 2 |
| LOW | 0 |
Build: PASS / FAIL
Tests: PASS / FAIL
Verdict: APPROVE | WARNING | BLOCK
Decision rules:
- APPROVE — no CRITICAL/HIGH, build + tests pass
- WARNING — HIGH issues only (can merge with caution)
- BLOCK — any CRITICAL issue or build failure
PR Review Mode
Phase 1 — FETCH
| Input | Action |
|---|---|
Number (42) |
Use as PR number |
URL (github.com/.../pull/42) |
Extract PR number |
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.
- 10d ago First seen · 159 lines · 22 tokens per session scan A fa4c839e02f6
code-review is a command published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,022 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.
Other commands, from other repositories
final-review
Command "final-review" from adriannoes/awesome-agentic-ai, covering final review - comprehensive pr review & testing, step 0: determine review pass, step 1: create or update the pr, step 2: launch three review agents in parallel and agent 1: codebase consistency reviewer.
code-review
Perform a thorough code review that verifies functionality, maintainability, and security before approving a change. Focus on architecture, readability, performance implications, and provide actionable suggestions for improvement.
deslop
Source: hamzafer/cursor-commands (MIT).
ship
Run the pre-launch checklist via parallel fan-out to specialist personas, then synthesize a go/no-go decision.
code-simplify
Simplify code for clarity and maintainability — reduce complexity without changing behavior.
review
Conduct a five-axis code review — correctness, readability, architecture, security, performance.