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 tsai09495/matt-pocock-engineering --skill code-reviewgit clone --depth 1 https://github.com/tsai09495/matt-pocock-engineeringWrote 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/tsai09495/matt-pocock-engineering/code-review)<a href="https://agentmods.dev/skills/tsai09495/matt-pocock-engineering/code-review"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/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/tsai09495/matt-pocock-engineering/code-review"><img src="https://agentmods.dev/badge/skills/tsai09495/matt-pocock-engineering/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00040 | $0.00972 |
| Opus 5.5 | $0.00016 | $0.00389 |
| Sonnet 5.5 | $0.00008 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Review the complete change on two independent axes:
- Standards — repository rules, correctness, safety, maintainability, and test quality.
- Spec — complete, correct, and scoped implementation of the originating request, ticket, spec, or PR.
Read quality-baseline.md. By default, the current agent performs the two passes sequentially and keeps their findings separate. Use independent or parallel reviewers only after following optional-enhancements.md.
Review-only mode never edits files, stages changes, or commits. When this skill is called inside an authorized implementation task, the caller may fix discrete confirmed findings that remain inside the original scope and then rerun review.
1. Establish the review target
Working tree
Use this when the user asks to review current, uncommitted, staged, unstaged, or untracked changes.
Inspect all of:
git status --short;- staged diff and summary;
- unstaged diff and summary;
- the full content of relevant untracked files, because ordinary
git diffomits them.
Exclude unrelated user changes from conclusions only when their separation is evident; otherwise state the uncertainty.
Fixed point
Use this for a branch, tag, commit, or PR. Resolve the supplied fixed point and normally compare git diff <fixed-point>...HEAD against the merge base. Record git log <fixed-point>..HEAD --oneline for intent. If the user names an exact commit range or PR diff, preserve that scope instead.
Fail clearly on an invalid reference or empty review target rather than silently choosing another baseline.
2. Establish evidence sources
Read applicable repository instructions such as AGENTS.md, CLAUDE.md, CONTRIBUTING.md, coding standards, domain glossaries, and ADRs.
Find the source requirement in this order:
- a path, ticket, PR, or acceptance criteria supplied by the user;
- references in commit messages or branch metadata;
- a matching spec under configured docs, specs, or local tracker paths;
- the user's current request.
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.
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 · 102 lines · 40 tokens per session scan A f2d8f2d76549
code-review is a skill published in the GitHub repository tsai09495/matt-pocock-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 972 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
refactor
Expert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior. Covers code smells, composing methods, moving features, organizing data, simplifying conditionals, method calls, and generalization. Triggers on: refactor, 重构, clean up, improve code, code smell, extract…
ase-code-lint
Lint source code for potential code quality problems. Use when the user wants to "lint" or "check" source code.
walkthrough
Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete. Captures a Change Summary, Verification Steps (commands + unit tests + automated browser testing outcomes), Visual Proof (screenshots/recordings embedded directly in the file), and a Review Gate (final diff + PR…