code-review

A guide for reviewing code changes, such as a branch diff or pull request. It examines the change from its purpose through its structure and individual lines, then groups findings by severity.

In plain words
What is it for?
Use it before merging changes, when auditing a pull request, or when checking the agent’s own implementation.
Why use it?
It turns a broad code check into clear, prioritized feedback about security, correctness, performance, or other risks without rewriting the author’s code.

Skill for Claude CodeCodex

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/andreaswasita/copilot-agents-dojo/code-review
Any agent
npx skills add andreaswasita/copilot-agents-dojo --skill code-review
Clone the repo
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojo

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,034 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 $0.00013 $0.01034
Opus 5 $0.00006 $0.00517
Sonnet 5 $0.00003 $0.00207
Haiku 4.5 $0.00001 $0.00103

Measured yesterday against content hash ca2fdaa55f7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

skills/code-review/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

Reviews diffs and PRs the way a senior engineer would: intent first, structure second, line-by-line third. Produces feedback grouped by severity (🔴 must / 🟡 should / 🟢 nit) with concrete suggestions. Does NOT rewrite the author's code — it directs, it does not replace.

When to Use

  • Reviewing a pull request, branch diff, or staged changes.
  • Auditing changes before merge.
  • Self-reviewing the agent's own output before presenting it.
  • Hunting for security, correctness, or performance regressions.
  • The user asks "does this look right?" about a code change.

Prerequisites

  • The view, grep, and glob Copilot tools to read code.
  • git available so diffs can be inspected (git diff main, git log).
  • Read access to the repository being reviewed.
  • For PR-scoped review: gh CLI authenticated to fetch PR metadata.

How to Run

1. Read the PR title, description, and linked issue.
2. List changed files (`git diff main --stat`) and assess scope.
3. Walk the diff with the `view` tool, file by file.
4. Apply the severity rubric below.
5. Emit a structured review block with concrete fixes.

Quick Reference

Phase Tool What to check
Intent PR description, linked issue Why does this change exist?
Scope git diff main --stat Files changed match stated intent
Correctness view on hot paths Logic, null/edge handling, off-by-one
Security grep for secrets, raw SQL, eval Injection, auth bypass, leaked secrets
Performance view on loops, queries N+1, unbounded allocations, missing indexes
Tests view on test files New paths actually covered

Procedure

Step 1: Understand Intent

Read the PR description, commit messages, and any linked issue. If intent is unclear, stop and ask the author — reviewing code whose purpose you don't understand wastes everyone's time.

Step 2: Structural Pass

Use git diff main --stat to size the change. Check:

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 13 tokens per session scan A ca2fdaa55f7a

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (51 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 1,034 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 2026-08-30.

Related

Other skills, from other repositories

pr-triage

PR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

rtk-ai/rtk · 64 tokens

code-review

Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…

ericrisco/rsc-harness · 90 tokens

code-review

Automated code review with checklist and quality gates.

modimihir07/agentic-os · 12 tokens

code-review

代码审查和质量分析技能。用于审查代码、发现潜在问题、提供改进建议。当用户请求代码审查、代码质量分析或最佳实践建议时使用。.

RTGS2017/NagaAgent · 42 tokens

fresh-eyes-review

This skill should be used as a mandatory final sanity check before git commit, PR creation, or declaring work done. Triggers on "commit", "push", "PR", "pull request", "done", "finished", "complete", "ship", "deploy", "ready to merge". Catches security vulnerabilities, logic errors, and business rule bugs that slip…

2389-research/fresh-eyes-review · 83 tokens

comprehensive-code-review

Use when performing code review on a PR, reviewing code changes before merge, or when a GitHub code review is requested or received - orchestrates parallel sub-agents for correctness and safety review.

futuregerald/futuregerald-claude-plugin · 43 tokens