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-askgit clone --depth 1 https://github.com/makedirectory/ModelPeerWhat 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 | $0.00010 | $0.00213 |
| Opus 5 | $0.00005 | $0.00106 |
| Sonnet 5 | $0.00002 | $0.00043 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
peer-ask 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 2d 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
Ask an independent peer the question in $ARGUMENTS with
model-peer ask <model> "<question>". Run model-peer doctor first if you are
unsure which peers are installed, and pick one that is not yourself.
The peer runs read-only in this working directory, so name files and symbols in the question rather than pasting excerpts, and ask one focused thing.
If $ARGUMENTS is empty, ask me what I want a second opinion on rather than
guessing.
Then report the peer's answer, say which model you asked, and state plainly whether you agree with it and why. Peers do not know this project's invariants; project rules win. Do not act on the advice without telling me.
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.
- 2d ago First seen · 22 lines · 10 tokens per session scan A 918ff8370ef2
peer-ask is a command published in the GitHub repository makedirectory/ModelPeer (1 stars, last pushed 15d ago), licensed MIT. It adds 10 tokens to every session and 213 once invoked, about $0.0001 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
team
Route a task to the right AI team + member (two-level team→member selection).
tmux-agent
Orchestrate parallel agents via tmux-mgr (start / list / complete / cleanup).
pi-askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis.
pi-research
Technical research via Gemini + WebSearch — dual-track search with Claude synthesis.
pi-ask-codex
Ask Codex CLI a question — get OpenAI's perspective alongside Claude's.
pi-ask-gemini
Ask Gemini a question — get Google's perspective alongside Claude's.