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 metaspartan/cybara --skill code-reviewgit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/code-review)<a href="https://agentmods.dev/skills/metaspartan/cybara/code-review"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/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/metaspartan/cybara/code-review"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00439 |
| Opus 5.5 | $0.00013 | $0.00176 |
| Sonnet 5.5 | $0.00007 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
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 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.
What it actually says
Code Review
Review changes against a consistent checklist. Be specific and kind; cite file:line.
Procedure
- Understand intent. Read the PR description / linked issue first. What is this change trying to do?
- Read the diff in full (
git diff main...HEAD). Then read the surrounding context, not just changed lines. - Check correctness first: does it do what it claims? Edge cases? Error handling? Off-by-ones? Null/empty inputs?
- Check security: untrusted input handling, injection (SQL/HTML/cmd), authz, secrets in code/logs, path traversal, unsafe deserialization.
- Check performance: N+1 queries, accidental O(n²), unbounded loops, missing pagination, large allocations in hot paths.
- Check maintainability: naming, duplication (DRY), dead code, overly long functions, missing tests, misleading comments.
- Verify tests actually cover the new behavior and aren't just happy-path.
Severity levels
- Blocking (must fix): correctness bugs, security holes, data loss, missing tests for risky logic.
- Important (should fix): poor error handling, perf issues, unclear naming.
- Nit (optional): style, minor refactors.
Writing good review comments
- Lead with the problem, not the solution. ("This will NPE if
useris null" beats "add a null check".) - Suggest a fix only after stating the issue.
- Distinguish blocking from nit explicitly.
- Praise good design decisions too — reviews aren't only for problems.
Output format
## Blocking
- path/file.ts:42 — <issue>
## Important
- path/file.ts:88 — <issue>
## Nits / Suggestions
- path/file.ts:120 — <nit>
## What's good
- <concise positive note>
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 First seen · 48 lines · 33 tokens per session scan A e1f42e2baaad
code-review is a skill published in the GitHub repository metaspartan/cybara (32 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 439 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.
antislop-code
Code comment hygiene for AI coding agents: remove generic AI-slop comments, keep the valuable ones, never touch the code.
superpowers-receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
electron-engineering
Guide architecture-sensitive Electron development and review. Use when creating or changing main, preload, or renderer responsibilities; IPC and capability boundaries; background execution; multi-window state ownership; window and platform behavior; lifecycle ownership; trust boundaries; or assumptions about the…
code-review-skill
Reviews code with feedback tailored to the developer's profile in session state.
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts…