Borrowing it
Nothing to install: this file belongs to compozy/skeeper. 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/compozy/skeeper/main/.agents/skills/cy-impl-peer-review/SKILL.mdgit clone --depth 1 https://github.com/compozy/skeeperWrote 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/compozy/skeeper/cy-impl-peer-review)<a href="https://agentmods.dev/skills/compozy/skeeper/cy-impl-peer-review"><img src="https://agentmods.dev/badge/skills/compozy/skeeper/cy-impl-peer-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/compozy/skeeper/cy-impl-peer-review"><img src="https://agentmods.dev/badge/skills/compozy/skeeper/cy-impl-peer-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 | $0.00129 | $0.02217 |
| Opus 5.5 | $0.00052 | $0.00887 |
| Sonnet 5.5 | $0.00026 | $0.00443 |
| Haiku 4.5 | $0.00013 | $0.00222 |
Grade A, and why
cy-impl-peer-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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Peer Review
Claude Opus pressure-tests an implementation diff via compozy exec. This skill runs that pressure-test only when the user explicitly asks for a review round after an implementation pass. It is decoupled from any PRD/task tracking system — the scope is the diff itself plus any optional context files the user names. The skill never auto-runs, auto-incorporates findings, auto-commits, or auto-loops additional rounds.
User Decisions
When this skill instructs the agent to ask whether to incorporate findings or run another round, it MUST use the runtime's dedicated interactive question tool — the tool or function that presents a question to the user and pauses execution until the user responds.
If the runtime does not provide such a tool, present the question as the complete assistant message and stop generating. Do not answer the question on the user's behalf.
Optional Inputs
All inputs are optional. Defaults make the common path cy-impl-peer-review with no arguments.
--files <path1,path2,...>— scope the review to explicit paths instead of the full branch diff.--context <path1,path2,...>— additional context files to feed Opus (e.g., a spec, ADR, design doc, RFC, README). The skill never assumes any of these exist.--base <git-ref>— base ref for the diff. Defaults tomain. Use--base HEAD~Nor--stagedfor narrower scopes.--out <dir>— output directory for round artifacts. Defaults to.peer-reviews/<UTC-timestamp>/at repo root.
Procedures
Step 1: Validate Input and Compute Scope
- Confirm the user has just completed (or paused) the implementation pass and explicitly asked to review the current state. Do not run review rounds during active editing.
- Resolve the diff scope:
- If
--filesis provided, verify each path exists and limit the diff to those paths. - If
--stagedis provided as the base, usegit diff --staged. - Otherwise run
git diff <base>...HEAD --name-only(default<base>ismain) to compute the changed file set. If the diff is empty, abort and tell the user there is nothing to review.
- If
- Resolve the artifact directory:
- Use
--outif provided. - Otherwise default to
.peer-reviews/<UTC-timestamp-YYYYMMDDTHHMMSSZ>/at the repository root. - Create the directory if it does not exist.
- Use
- Read
.agents/skills/cy-impl-peer-review/references/readiness-checks.mdand verify every readiness marker passes (build/tests green, no committed.tmp/orai-docs/, diff is non-empty, no obvious WIP markers in changed files, codegen co-ship if contracts touched, migration co-ship if schema touched, reviewable size). If any marker fails, report the failed markers and abort — Opus review on a broken or incomplete change wastes credit and produces noise. - Determine the next review round number by listing existing
impl-review-result-round*.jsonfiles in the artifact directory. Start atround1when none exist.
What ships with it
2 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.
- 1mo ago First seen · 114 lines · 129 tokens per session scan A 18ee227fe309
cy-impl-peer-review is a skill published in the GitHub repository compozy/skeeper (89 stars, last pushed 4mo ago), licensed MIT. It adds 129 tokens to every session and 2,217 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…