code-review

A code-review workflow for checking GitHub Copilot changes for correctness, security, code quality, and maintainability.

In plain words
What is it for?
Reviewing pull requests, branch differences, and other added or changed code.
Why use it?
It gives reviewers a structured way to catch bugs, breaking changes, security issues, and unnecessarily complicated code in modified files.

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/asteasolutions/ai-toolkit/code-review
Any agent
npx skills add asteasolutions/ai-toolkit --skill code-review
Clone the repo
git clone --depth 1 https://github.com/asteasolutions/ai-toolkit

Made for: Claude Code, Codex.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 516 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 $0.00038 $0.00516
Opus 5 $0.00019 $0.00258
Sonnet 5 $0.00008 $0.00103
Haiku 4.5 $0.00004 $0.00052

Measured 2d ago against content hash 5011f1484389, 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 2d 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.

.claude/skills/code-review/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Code Review

When reviewing this change, apply BOTH of the following skills as complete rubrics. Do not skip either pass.

  1. thermo-nuclear-review - bugs, breaking changes, security issues, developer-experience regressions, and feature-gate leaks. Only added or modified code.
  2. thermo-nuclear-code-quality-review - code-judo / structural simplification, 1k-line file growth, spaghetti branching, boundaries, and abstraction quality.

If those skills are not already in context, load them by name from sibling skill directories. If they cannot be loaded, still run both passes using the same intent: a harsh correctness/security audit of the diff, then a harsh maintainability audit of the same diff.

Apply any repository instructions (AGENTS.md, .github/copilot-instructions.md, path-specific *.instructions.md) as constraints on findings and remediations. Those files are the source of repo-specific policy. This skill is not.

Workflow

  1. Determine review scope from the PR, branch, or changed files. Gather the diff and enough surrounding file context to evaluate the change without guessing.
  2. Apply the correctness/security rubric to the diff. Trace cross-module side effects. Do not report pre-existing issues in untouched code. Do not present unfinished research when the related code is in this repository.
  3. Apply the code-quality rubric to the same diff. Search for structural simplifications, not just local cleanup.
  4. Synthesize one review. Findings first, deduplicated across both passes. Weight overlapping findings more heavily. Resolve disagreements with your own judgment. Keep summaries brief.

Output

Prefer a small number of high-conviction comments over a long list of nits.

Priority order:

  1. Correctness, breakage, and security
  2. Structural code-quality regressions and missed code-judo simplifications
  3. Spaghetti / branching complexity, boundary leaks, file-size explosions
  4. Remaining maintainability issues that still matter

For each finding include file references, evidence, and a concrete remediation that fits this repository's instructions. Do not rubber-stamp "it works" if the change makes the codebase messier or leaves an obvious simpler structure unused.

Read the full file on GitHub · 38 lines

Files

What ships with it

1 file 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.

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. 2d ago First seen · 38 lines · 38 tokens per session scan A 5011f1484389

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository asteasolutions/ai-toolkit (5 stars, last pushed 6d ago), licensed MIT. It adds 38 tokens to every session and 516 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens