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 Cristhianzl/claude-skills-czl --skill reviewing-codegit clone --depth 1 https://github.com/Cristhianzl/claude-skills-czlWrote 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/cristhianzl/claude-skills-czl/reviewing-code)<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/reviewing-code"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/reviewing-code/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/cristhianzl/claude-skills-czl/reviewing-code"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/reviewing-code.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 | $0.00119 | $0.03399 |
| Opus 5.5 | $0.00048 | $0.01360 |
| Sonnet 5.5 | $0.00024 | $0.00680 |
| Haiku 4.5 | $0.00012 | $0.00340 |
Grade A, and why
reviewing-code 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing Code
Produce a PR review that reads like a competent engineer wrote it after doing the work. It applies a security lens, a comprehension audit, and structural checks, triages findings by severity internally, and delivers them as first-person prose — evidence first, disposition in every finding, copy-paste-safe for GitHub.
Read first (always)
List learnings/ and read every file relevant to the current PR (the touched modules, frameworks, or risk areas). Project-specific review conventions, severity adjustments, banned patterns, or scope rules live there and override the defaults in this SKILL.md. If a learning conflicts with this file, the learning wins — mention it to the user.
Tradeoff — when to apply, when to lighten up
Apply the full discipline (security lens + comprehension audit + checklist + grep) for production-bound PRs touching shared services, payments, auth, user data, AI runtime, or anything externally observable.
Lighten formality for: docs-only changes, lockfile bumps with no API change, single-line typo fixes, internal-tooling-only changes behind a feature flag not yet enabled. Still apply the security lens — even doc PRs can leak secrets in examples.
Hard rules — output is a chat message, not a side effect
Apply the same restrictions as the writing-pull-requests skill, plus review-specific ones:
- Never run
gh pr review,gh pr comment, or any GitHub-mutating command. The user posts the review themselves. - Never run
git commit,git add,git push. Only the human commits. - Never write the review to a file. Output goes in the chat.
- Never use
#Nanywhere in the output — GitHub auto-links it to PR/issueN. - Never hard-wrap prose: one paragraph = one logical line; Enter only at paragraph/list/heading boundaries. Manual 72/80-column wrapping is the strongest "a tool wrote this" tell.
- Write like a person — first person, evidence first, findings as complete sentences with the disposition inside them. No finding IDs, no
**File:**-style label lines, no emoji headers, no metadata tables. Full voice rules:references/output-format.md. - Never
@mentionusers unless the user explicitly asks. - Never include
Fixes #N,Closes #N,Resolves #N— they auto-close issues on merge. - Never paste full file contents — link with
path/to/file.ts:42and quote 3-10 relevant lines max. - Never use absolute local paths (
/Users/...,/home/...). Use repo-relative paths only. - Match the PR's language. The review or comment is written in the language of the PR itself (title, description, discussion): a pt-BR PR gets a pt-BR review, an English PR gets English. Code identifiers, paths, and quoted code stay verbatim. Mixed or unclear → default to English. (This is the one exception to the English-always baseline.)
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +12 lines f80558822576
- 1mo ago Changed · +2 lines · +18 tokens per session 9b45cd41c156
- 1mo ago First seen · 186 lines · 101 tokens per session scan A 4c97494c7f2c
reviewing-code is a skill published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed 1mo ago), licensed MIT. It adds 119 tokens to every session and 3,399 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
tech-debt-audit
Thorough, file-cited technical debt audit across 9 dimensions using AST-grep (tree-sitter), grep, LSP, and language-native tooling. Produces TECHDEBTAUDIT.md with severity, effort estimates, and prioritized fixes. Use when asked for codebase health check, tech debt audit, architecture review, code quality assessment…