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 jkm-4314/claude-code-skills --skill peer-reviewgit clone --depth 1 https://github.com/jkm-4314/claude-code-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/jkm-4314/claude-code-skills/peer-review)<a href="https://agentmods.dev/skills/jkm-4314/claude-code-skills/peer-review"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/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/jkm-4314/claude-code-skills/peer-review"><img src="https://agentmods.dev/badge/skills/jkm-4314/claude-code-skills/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 | $0.00047 | $0.05458 |
| Opus 5 | $0.00023 | $0.02729 |
| Sonnet 5 | $0.00009 | $0.01092 |
| Haiku 4.5 | $0.00005 | $0.00546 |
Grade C, and why
peer-review scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$REVIEW_DIR" How it starts
The opening of the file, as written. The whole thing — 450 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Peer Review
📦 This skill is also part of a larger collection: claude-code-skills — project bootstrap, persistent session memory, and peer review. Clone the repo if you want all of them.
Orchestrate iterative review of specs or code by Codex (GPT-5.5) until both Claude and Codex agree the work is production-ready.
Installation
-
Prerequisites:
- Claude Code installed and configured
- Codex CLI v0.125.0 or later in PATH, authenticated against an OpenAI account that can call
gpt-5.5 - Run
codex --versionto verify
-
Install the skill:
- Save this
SKILL.mdto~/.claude/skills/peer-review/SKILL.md(Linux/macOS) or%USERPROFILE%\.claude\skills\peer-review\SKILL.md(Windows) - Restart Claude Code, or start a new session, so the skill is discovered
- Save this
-
Optional — slash command:
- Invoke explicitly with
/peer-review specor/peer-review code - Otherwise the skill triggers automatically after spec writing or code completion (unless the user opts out)
- Invoke explicitly with
-
Verify: Ask Claude "run the peer-review skill on this spec" and confirm Codex is invoked.
Modes
- spec — Review a specification document
- code — Review code changes (git diff)
Determine mode from context or from the argument passed (e.g., /peer-review spec).
Bypass
Do NOT run this skill ONLY if:
- User explicitly said one of: "skip review", "no review", "don't review", "bypass review"
- User has previously marked THIS SPECIFIC PROJECT as non-production in conversation
Do NOT infer bypass. When in doubt, ask: "Should I run the Codex review for this?"
Orchestration
Step 0: Preflight Validation
Before the first review round, verify Codex CLI availability:
codex --version
- If
codexis not in PATH: hard fail — report "Codex CLI not found" and abort - If version is below 0.125.0: hard fail — required flags (
--ignore-user-config,-o) may not exist - If critical flags are unavailable: hard fail — sandbox enforcement would be compromised
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.
- 10d ago First seen · 450 lines · 47 tokens per session scan C cf17dd89e920
peer-review is a skill published in the GitHub repository jkm-4314/claude-code-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 5,458 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
shipkit-review-shipping
Review changes across 12 quality dimensions and report findings. Use after a chunk of work or before commit.
shipkit-prompt-audit
Audit LLM prompt pipeline architecture — decomposition, parallelization, chain integrity, schema validation, fallback paths. Finds structural issues no linter catches.
shipkit-review-planning
Internal reviewer — assesses planning artifact alignment. Checks definitions agree, specs cover roadmap, no gaps. A per-unit reviewer invoked by a caller (the engine in steered mode or a direction/planning caller), not for direct use.
shipkit-review-direction
Internal reviewer — assesses strategic artifact coherence. Checks vision/why alignment, goal completeness, stage realism. The Direction coherence-review gate, dispatched by the engine (via shipkit-direction), not for direct use.
review-implementing
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
code-auditor
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.