code-review

code-review is a skill for Claude Code from jaktestowac/awesome-copilot-for-testers. It costs 76 tokens per session (836 once invoked), scanned A, original, MIT.

A quick review of a small code change, one file, or a short snippet for correctness, readability, tests, security, performance, and obvious risks.

In plain words
What is it for?
Use it for small diffs and routine low-risk changes, including checking missing tests, documentation, standards violations, and short- and long-term improvements.
Why use it?
It gives concise, actionable feedback when a change needs a fast sanity check before a more detailed review.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Install

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.

agentmods
npx agentmods add skills/jaktestowac/awesome-copilot-for-testers/code-review
Any agent
npx skills add jaktestowac/awesome-copilot-for-testers --skill code-review
Clone the repo
git clone --depth 1 https://github.com/jaktestowac/awesome-copilot-for-testers

Made for: Claude Code.

Wrote 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.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/code-review.svg)](https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/code-review)
Your own site
<a href="https://agentmods.dev/skills/jaktestowac/awesome-copilot-for-testers/code-review"><img src="https://agentmods.dev/badge/skills/jaktestowac/awesome-copilot-for-testers/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.00836
Opus 5 $0.00038 $0.00418
Sonnet 5 $0.00015 $0.00167
Haiku 4.5 $0.00008 $0.00084

Measured 6d ago against content hash 6d12d0d72150, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 6d 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.

plugins/code-review/skills/code-review/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quick Code Review

This skill applies a consistent, lightweight assessment to a small code change. It focuses on key principles of code quality:

  • Safety (avoid incorrect assumptions; call out uncertain areas)
  • Clarity (structuring comments in positive and actionable form)
  • Coverage (address correctness, tests, security, performance, readability)

When to Use

  1. The user asks for a quick review of a small diff, single file, or snippet.
  2. A change needs a fast sanity check before a fuller review.
  3. You need a compact checklist for a routine, low-risk change.

For large or multi-file pull requests, legacy audits, test-automation suites, or high-risk paths (auth, payments, data flows), use code-review-advanced instead.

Skill Behavior

  • Start with a summary: what is changing, why, and whether the implementation is aligned with goals.
  • Categorize findings:
    • ✅ Strengths / wins
    • ⚠️ Concerns / risks
    • 🛠️ Suggestions / improvements
  • Provide short-term fix guidance plus long-term design thoughts.
  • Flag any missing tests, docs, or standards violations.
  • Respect context: mention the module/file/function names (not generic: "the code").

Quick Review Checklist

  1. Correctness

    • Does the code do what the ticket/PR describes?
    • Are edge cases handled (null, errors, concurrency, format)?
    • Any regression risk from changed behavior?
  2. Maintainability

    • Is the implementation easy to read and reason about?
    • Are abstractions and naming appropriate?
    • Any repeated logic that should be refactored?
  3. Testing

    • Are unit and integration tests present and relevant?
    • Do tests cover both normal and boundary cases?
    • Are tests deterministic and fast?
  4. Security & Privacy

    • Are user inputs validated/escaped and untrusted data treated carefully?
    • Any secrets in code, logs, or config?
    • Does the change introduce new permissions, cross-origin, or auth gaps?
  5. Performance

    • Any obvious O(N^2) loops or hot-path allocations?
    • Are caching and batching used when appropriate?
    • For network I/O, is retry/backoff and timeout handling present?

Read the full file on GitHub · 90 lines

Changes

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.

  1. 6d ago First seen · 90 lines · 76 tokens per session scan A 6d12d0d72150

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository jaktestowac/awesome-copilot-for-testers (113 stars, last pushed 11d ago), licensed MIT. It adds 76 tokens to every session and 836 once invoked, about $0.0004 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.