Borrowing it
Nothing to install: this file belongs to dzhng/duet-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dzhng/duet-agent/main/.agents/skills/review/SKILL.mdgit clone --depth 1 https://github.com/dzhng/duet-agentWrote 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/dzhng/duet-agent/review)<a href="https://agentmods.dev/skills/dzhng/duet-agent/review"><img src="https://agentmods.dev/badge/skills/dzhng/duet-agent/review.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 | $0.00091 | $0.00454 |
| Opus 5 | $0.00046 | $0.00227 |
| Sonnet 5 | $0.00018 | $0.00091 |
| Haiku 4.5 | $0.00009 | $0.00045 |
Grade A, and why
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 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.
This is a copy
100% identical to review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Review
A finished change earns "done" only after three lenses pass: its shape, its diff, and its docs. Each has a specialist skill. This skill owns only what they can't — the order they run in, the loop between them, and one verdict.
Workflow
- Scope. Fix the diff under review and confirm it's substantive; skip the whole pass for trivial edits.
- Shape — refactor-clean. Run it first, while restructuring is cheap and before you audit a diff that's about to move.
- Diff — code-review. Audit the settled shape. A finding that forces a structural change sends you back to step 2, not onward.
- Docs — write-docs. Update the docs this change touched. Then trace the link chain from the root README down to each one: every link on the path still resolves, and the hub-to-leaf flow still reads in order.
- Report. One verdict across all three passes — what each found, what you changed, what you left and why. Done only when every pass is clean or resolved.
Rules
- When you enter a pass, read its skill — the rules live there, not here.
- Order governs presentation, not disclosure: surface a finding the moment you hit it, even when a later pass owns it.
- Loop, don't cascade: a later fix that reopens an earlier pass returns there. Stop when a full pass adds nothing.
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 · 35 lines · 91 tokens per session scan A 793308592d56
review is a skill published in the GitHub repository dzhng/duet-agent (42 stars, last pushed 5d ago), licensed Apache-2.0. It adds 91 tokens to every session and 454 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to review, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
evaluator-review-contract
Internal Auto-Harness evaluator skill for sprint contract review before implementation. Use only inside the Evaluator subagent during review mode.
open-code-review
Performs AI-powered code review on Git changes using the ocr CLI from alibaba/open-code-review. Use when the user asks to review code, review a pull request, review staged/unstaged changes, review a commit, or compare branches for code quality issues. Produces line-level review comments and can automatically apply…
open-code-review-delegate
Delegation mode for open-code-review (OCR). Instead of OCR calling an LLM endpoint, this skill instructs the host agent to perform the code review itself, using OCR only for deterministic engineering: file selection and rule resolution. Use when the host agent should drive the review with its own LLM capabilities.
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
code-review
Paranoid architect review of code changes for bugs, security, missing tests, and undocumented assumptions. Works on local git diffs OR a GitHub pull request (e.g. owner/repo N). For PRs, can post findings as line-level review comments.