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 commands/makedirectory/modelpeer/peer-reviewgit 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/commands/makedirectory/modelpeer/peer-review)<a href="https://agentmods.dev/commands/makedirectory/modelpeer/peer-review"><img src="https://agentmods.dev/badge/commands/makedirectory/modelpeer/peer-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 | $0.00009 | $0.00221 |
| Opus 5 | $0.00005 | $0.00111 |
| Sonnet 5 | $0.00002 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
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 3d 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.
What it actually says
Run an independent cross-model review of the current working tree with
model-peer review, passing $ARGUMENTS as the focus when it is non-empty.
Every installed model reviews the same diff without seeing the others' conclusions, then a synthesizer reconciles them. Reviewers run at the same time, so this takes a few minutes and looks busy: stderr carries interleaved progress from several models, and nothing reaches stdout until the whole panel has finished. Let it finish.
Then:
- Report the synthesized findings, grouped by severity, without softening them.
- For each finding, say whether you agree and why. A peer does not know this project's invariants; project rules win over generic advice.
- Do not apply any fix unless I ask for it.
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.
- 3d ago First seen · 24 lines · 9 tokens per session scan A 6c8a212d7cb3
peer-review is a command published in the GitHub repository makedirectory/ModelPeer (1 stars, last pushed 16d ago), licensed MIT. It adds 9 tokens to every session and 221 once invoked, about $0.0000 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 commands, from other repositories
ssh-keys
Manage SSH keys across hosts — generate, sync, list status, or delete.
pi-code-review
Adversarial code review via Codex — break confidence in changes, not validate them.
setup
Install the claude-pace statusline bundled with this plugin.
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.
voice-test
Test the complete AudioBash voice transcription pipeline including all providers, API key configuration, and agent mode prompts.