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 2ykwang/agent-skills --skill code-review-reportgit clone --depth 1 https://github.com/2ykwang/agent-skillsWrote 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/2ykwang/agent-skills/code-review-report)<a href="https://agentmods.dev/skills/2ykwang/agent-skills/code-review-report"><img src="https://agentmods.dev/badge/skills/2ykwang/agent-skills/code-review-report.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.00734 |
| Opus 5 | $0.00041 | $0.00367 |
| Sonnet 5 | $0.00016 | $0.00147 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
code-review-report 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 8d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Report
Build a single-file HTML report a reviewer reads before digging through the raw diff. A diff shows what changed; it doesn't show why, what was rejected, or what's still missing. Filling that gap with the context accumulated in this conversation is what separates this from a diff viewer.
1. Collect the change
Check the change with git status and git diff. Default scope: current branch vs the default branch, plus the uncommitted working tree.
git diff <base>...HEAD(committed),git diff HEAD(uncommitted)- Untracked files don't appear in diffs — find them with
git statusand read them directly.
If the scope is mixed or contains unrelated changes, ask the user. Exclude unrelated changes or mark them separately.
2. Collect the working context
Gather from this conversation the things a diff never records:
- What was changed and why
- Design decisions and their reasons, rejected alternatives, tradeoffs
- Unfinished work and next steps
- Concerns raised and reversals made along the way
If the conversation lacks this (e.g., the skill was invoked fresh), reconstruct from git log, commit messages, PRs, and related docs. If still empty, ask the user.
3. Extract review points
Hand the changed code and the working context to subagents, and collect what they flag as P1–P3 findings. Read references/review-perspectives.md for the perspective list and the subagent prompt skeleton. The context injection is the point — without it you only get surface-level remarks, not findings like spec mismatches or contradictions between decisions. For large changes, run one subagent per perspective in parallel.
4. Write the HTML
Start from assets/template.html. Follow references/report-structure.md for sections and references/style-guide.md for visual rules. Two things are non-negotiable:
- Syntax highlighting on code blocks (add
language-*classes) - Bidirectional anchors between change details and the review checklist
Write the report in the language the user works in: translate the template's headings and set <html lang>. Keep code as-is. Before finalizing, run the self-check at the end of references/report-structure.md.
What ships with it
8 files 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.
- 8d ago First seen · 58 lines · 81 tokens per session scan A ca119f1cdbe1
code-review-report is a skill published in the GitHub repository 2ykwang/agent-skills (19 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 734 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.
Other skills, from other repositories
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…
understand
Review and understand freshly AI-generated code. Scans the current repo's uncommitted/branch changes and builds a Claude-style light-themed two-column webpage — left is the project folder tree of changed files, right is the selected file's syntax-highlighted diff (additions/deletions clearly distinguished from…
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…
phpunit-test-team-reviewing
Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger phrases like "team review these tests", "consensus review the tests in PR.
phpunit-test-reconciling
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.
issue-analyzing
Use this skill when the user asks to analyze a specific GitHub issue, understand what area of code an issue affects, assess an issue's scope, or research the code context around an issue — example triggers like "analyze issue.