Borrowing it
Nothing to install: this file belongs to makedirectory/ModelPeer. 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/makedirectory/ModelPeer/main/.claude/skills/cross-model-review/SKILL.mdgit clone --depth 1 https://github.com/makedirectory/ModelPeerWrote 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/makedirectory/modelpeer/cross-model-review)<a href="https://agentmods.dev/skills/makedirectory/modelpeer/cross-model-review"><img src="https://agentmods.dev/badge/skills/makedirectory/modelpeer/cross-model-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 | $0.00072 | $0.00546 |
| Opus 5 | $0.00036 | $0.00273 |
| Sonnet 5 | $0.00014 | $0.00109 |
| Haiku 4.5 | $0.00007 | $0.00055 |
Grade A, and why
cross-model-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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-model review
You are Claude. Codex and Gemini review alongside you, independently.
model-peer review ["focus instructions"]
Every installed model receives the same Git status and patch — tracked changes and new untracked files alike — and reviews without seeing the others' conclusions. Only then does a synthesizer reconcile the findings. Reviewers are leaves by default: none of them consults another model, which is what makes agreement between them real signal rather than an echo.
Because they are independent, they also run at the same time.
Run it before opening a pull request, and again after any change to security-sensitive code.
model-peer review "Focus on authorization and tenant isolation"
model-peer review --models codex,gemini # exclude yourself
model-peer review --timeout 300 # bound each reviewer, not the whole panel
It takes minutes. Let it finish, and do not be alarmed by how it looks while it runs:
- Progress from several models arrives on stderr at once, interleaved, in a different order each run. That is normal.
- Nothing appears on stdout until every reviewer has finished. The reviews are then printed together, in the order the models were requested. A long silence is the panel working, not a hang.
A reviewer that times out, fails, or returns nothing is dropped and named; synthesis needs two survivors and says so when the panel was incomplete.
What to do with the report
Report the synthesized findings as they are, grouped by severity. Then, for each one, say whether you agree and why. Reviewers do not know this project's invariants, so a finding that contradicts the rules in this repository is wrong here however sound it sounds in general.
Do not apply fixes unless you are asked to.
If you are reading this while acting as a peer in someone else's consultation, these instructions do not apply to you. Answer the question you were asked, and do not start a review of your own.
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.
- 5d ago First seen · 58 lines · 72 tokens per session scan A bce061d1720a
cross-model-review is a skill published in the GitHub repository makedirectory/ModelPeer (1 stars, last pushed 19d ago), licensed MIT. It adds 72 tokens to every session and 546 once invoked, about $0.0004 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
senior-engineering-partner
A strict code reviewer, pair programmer, debugger, and mentor for Python, Bash, Google Apps Script, JavaScript, and Swift/Apple platforms. Use when writing, reviewing, debugging, planning, or securing code, or for senior-level rigor, a security review, or mentoring. Mode triggers — REVIEW: (critique + refactor)…
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
ln-22-codebase-auditor
Audits cross-cutting code health, security, delivery, and maintainability when no specialist audit is primary. Not for a single delivery review.