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 agentmods add skills/arroyo-gonzalo/codex-devkit/code-reviewnpx skills add Arroyo-Gonzalo/codex-devkit --skill code-reviewgit clone --depth 1 https://github.com/Arroyo-Gonzalo/codex-devkitWhat 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 | $0.00060 | $0.01375 |
| Opus 5 | $0.00030 | $0.00687 |
| Sonnet 5 | $0.00012 | $0.00275 |
| Haiku 4.5 | $0.00006 | $0.00137 |
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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Purpose
Evaluate a code change for correctness, safety, compatibility, and maintainability.
Prioritize defects with real impact over subjective style preferences.
Do not modify the code unless the user explicitly requests corrections.
Review workflow
1. Establish the review scope
Determine what must be reviewed:
- current working tree changes;
- staged changes;
- a commit;
- a branch comparison;
- a pull request;
- specific files;
- a supplied patch or diff.
Identify the intended behavior of the change before judging its implementation.
Do not expand the review into unrelated parts of the repository without a concrete reason.
2. Inspect repository guidance
Before reviewing:
- read applicable AGENTS.md files;
- inspect relevant project documentation;
- identify language, framework, runtime, and package manager;
- inspect testing, linting, formatting, and build conventions;
- understand established architectural patterns.
Review the change against the repository's actual conventions, not generic preferences.
3. Understand the change
Determine:
- what behavior is being added or changed;
- which modules and contracts are affected;
- what assumptions the implementation makes;
- what data enters and leaves the changed code;
- whether persistence, authentication, authorization, concurrency, or external integrations are involved.
Read enough surrounding code to understand the changed behavior, but avoid scanning the entire repository.
4. Review functional correctness
Check for:
- incorrect conditions;
- incomplete branches;
- wrong return values;
- broken state transitions;
- incorrect asynchronous behavior;
- unhandled errors;
- improper null or undefined handling;
- invalid assumptions about data;
- incorrect ordering;
- off-by-one errors;
- unintended side effects;
- behavior that contradicts the requested change.
Focus first on defects that could produce incorrect results.
5. Review contracts and compatibility
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.
- 2d ago First seen · 287 lines · 60 tokens per session scan A 43a13e643356
code-review is a skill published in the GitHub repository Arroyo-Gonzalo/codex-devkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,375 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.