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 selmakcby/claude-agents-skills --skill code-reviewgit clone --depth 1 https://github.com/selmakcby/claude-agents-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/selmakcby/claude-agents-skills/code-review)<a href="https://agentmods.dev/skills/selmakcby/claude-agents-skills/code-review"><img src="https://agentmods.dev/badge/skills/selmakcby/claude-agents-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/selmakcby/claude-agents-skills/code-review"><img src="https://agentmods.dev/badge/skills/selmakcby/claude-agents-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 | $0.00048 | $0.00743 |
| Opus 5 | $0.00024 | $0.00371 |
| Sonnet 5 | $0.00010 | $0.00149 |
| Haiku 4.5 | $0.00005 | $0.00074 |
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
When to trigger
- Immediately after new or modified code
- Before commit / PR
- When user asks for
/code-review
Review approach
Multi-agent review with confidence filtering:
- CLAUDE.md compliance — does the code follow project rules?
- Bug detector — obvious bugs in the diff
- History analyzer — git context to understand intent
Each issue is scored 0–100. Findings below threshold (default 80) are filtered out.
What to check
Clarity
- Names (variables, functions, files) — do they say what they do?
- Structure — is it easy to scan?
- Cognitive load — how much do you hold in your head to understand it?
Correctness
- Edge cases: null, undefined, empty array, boundary values
- Error paths: are they handled? Do they fail loudly or silently?
- Async: await missing? Race conditions? Promise rejections caught?
- Off-by-one errors in loops / slicing
Performance
- N+1 queries (especially around ORM usage)
- O(n²) algorithms on large collections
- Unnecessary re-renders (React)
- Missing memoization for expensive computations
- Synchronous I/O in hot paths
Consistency
- Matches project style guide (CLAUDE.md, rules/)
- Immutable patterns used
- Function size under 50 lines
- Nesting 4 levels max
Tests
- Is there a test for the new behavior?
- Edge cases covered?
- Mocks realistic (no "happy path only")?
- Tests independent (no shared state)?
Dead code
- Unused imports
- Unreachable branches
- TODO comments that should be done or deleted
- Commented-out code
Severity levels
- CRITICAL — do not commit. Breaks production, security hole, data loss risk.
- HIGH — fix before next release. Real bug users will hit.
- MEDIUM — fix when you're in the area. Code smell, minor inefficiency.
- LOW — nice-to-have. Style preference, optional refactor.
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 · 101 lines · 48 tokens per session scan A 47886a937fd4
code-review is a skill published in the GitHub repository selmakcby/claude-agents-skills (124 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 743 once invoked, about $0.0002 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…