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/tslateman/duet/reviewnpx skills add tslateman/duet --skill reviewgit clone --depth 1 https://github.com/tslateman/duetWrote 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/tslateman/duet/review)<a href="https://agentmods.dev/skills/tslateman/duet/review"><img src="https://agentmods.dev/badge/skills/tslateman/duet/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 | $0.00061 | $0.01148 |
| Opus 5 | $0.00030 | $0.00574 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
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 4d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Code Review
Overview
Code review that captures context, not just correctness. Grounded in Bacchelli & Bird's research on modern code review, which found that code review's primary value is knowledge transfer, not defect detection. Beyond finding bugs, document the why, concerns raised, alternatives considered, risks accepted. This creates organizational memory for future maintainers.
Use this for PRs, local changes, or architecture review, any code where you want to preserve the reasoning, not just the verdict.
Review Workflow
1. Understand the Change
Before commenting, understand intent:
- What problem does this solve?
- What was the previous state?
- What constraints shaped the solution?
Read the PR description, linked issues, and recent commits.
If context is missing, ask before reviewing.
2. Evaluate on Multiple Dimensions
Correctness, Does it work?
- Logic errors, edge cases, error handling
- Does it match stated requirements?
Design, Is this the right approach?
- Does it fit existing patterns in the codebase?
- Are there simpler alternatives?
- Will this scale if assumptions change?
Maintainability, Can others work with this?
- Is the code readable without comments?
- Are names clear and consistent?
- Is complexity justified?
Risk, What could go wrong?
- Performance implications
- Security considerations
- Breaking changes, backwards compatibility
- Operational concerns (monitoring, debugging)
3. Document Your Review
Structure feedback for the record:
## Summary
[1-2 sentence assessment: approve, request changes, or needs discussion]
## What This Changes
[Brief description of the change and its purpose]
## Feedback
### Must Address
- [Blocking issue] — [Why it matters]
### Should Consider
- [Non-blocking suggestion] — [Trade-off or alternative]
### Observations
- [Pattern noticed, question raised, or context captured]
## Concerns for the Record
[Risks accepted, alternatives rejected, assumptions made; future maintainers need this]
## Alternatives Considered
[Other approaches discussed and why they were rejected]
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.
- 4d ago First seen · 193 lines · 0 tokens per session scan A 311c242765b0
review is a skill published in the GitHub repository tslateman/duet (1 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,148 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
to-plan
Capture the chat into .task/task/ .md with ## Description plus ## Plan (Goal/Touches/Logic) — the deepest one-task capture.
roadmap-to-workflow
Fan an approved .task/roadmap/ .md out to a dynamic Workflow — parallel planning, serialized implementation, dependency-ordered waves.
to-roadmap
Capture a multi-task initiative into .task/roadmap/ .md — a phase-grouped backlog of ready-to-pick-up items.
self-improve
Self-improve this skills repo — surface and (safely) apply quality improvements across four parallel read-only lenses (Clarity, Leanness, Coverage, Ergonomics). Sibling of /self-audit — audit fixes rule violations, improve raises quality where no rule is broken. Local meta-skill, independent of the /task: pipeline.
to-task
Capture the chat (or a roadmap item) into .task/task/ .md — ## Description only, no ## Plan.
self-audit
Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.