Borrowing it
Nothing to install: this file belongs to AlexanderMattTurner/agent-glovebox. 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/AlexanderMattTurner/agent-glovebox/main/.claude/skills/peer-review/SKILL.mdgit clone --depth 1 https://github.com/AlexanderMattTurner/agent-gloveboxWrote 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/alexandermattturner/agent-glovebox/peer-review)<a href="https://agentmods.dev/skills/alexandermattturner/agent-glovebox/peer-review"><img src="https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/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/alexandermattturner/agent-glovebox/peer-review"><img src="https://agentmods.dev/badge/skills/alexandermattturner/agent-glovebox/peer-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.00834 |
| Opus 5.5 | $0.00040 | $0.00334 |
| Sonnet 5.5 | $0.00020 | $0.00167 |
| Haiku 4.5 | $0.00010 | $0.00083 |
Grade A, and why
peer-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer Review Skill
A separate read-only agent reviews the diff so the author’s intent does not color the review. Use this before shipping or whenever an unbiased look at pending changes is wanted.
Workflow
1. Capture the diff
Compute the review target and keep the text: the diff against the base branch (git diff "$CLAUDE_CODE_BASE_REF"...HEAD), or uncommitted work (git diff / git diff --cached). Get its changed paths, then capture git log -n 30 --no-merges --oneline -- <changed paths> so the review can distinguish a first defect from a repeated local repair.
2. Launch the reviewer
Invoke the code-reviewer subagent (.claude/agents/code-reviewer.md) via the Agent tool, passing the diff and path history from step 1 in the prompt — the agent is read-only (Read/Grep/Glob, model: opus) with no shell, so it cannot fetch either itself. It reads the surrounding files for context on its own.
3. Triage and fix
For each finding, assess validity first — the reviewer can be wrong. Then:
- Blocker / Should-fix: fix it, re-running the project’s tests/lint as needed.
- Nit: apply if cheap; otherwise note and move on.
- Invalid: state why in one line and skip.
Do not weaken or delete tests to make a finding “go away” (see CLAUDE.md).
4. Re-review to a fixed point
After fixing, launch a fresh code-reviewer pass with the updated diff — fixes introduce their own bugs and the prior review is now stale. Stop when a full pass returns nothing actionable. The cap is at most three passes (.claude/rules/development-workflow.md § Self-critique); if findings persist there, summarize what is left in the report and proceed rather than looping silently.
5. Report
Summarize what the reviewer flagged, what you fixed, and anything deliberately deferred.
When NOT to use
- Creating a PR end-to-end — use
pr-creation(it already runs its own critique loop). - Trivial edits (typo fixes, single-line config tweaks) — say so and skip.
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 Changed abd28fd9a5c5
- 1mo ago First seen · 68 lines · 100 tokens per session scan A 2cf21d5e0f09
peer-review is a skill published in the GitHub repository AlexanderMattTurner/agent-glovebox (68 stars, last pushed today), licensed Apache-2.0. It adds 100 tokens to every session and 834 once invoked, about $0.0004 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"…
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…
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…
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…