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-consult/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-consult)<a href="https://agentmods.dev/skills/makedirectory/modelpeer/cross-model-consult"><img src="https://agentmods.dev/badge/skills/makedirectory/modelpeer/cross-model-consult/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/makedirectory/modelpeer/cross-model-consult"><img src="https://agentmods.dev/badge/skills/makedirectory/modelpeer/cross-model-consult.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 | $0.00099 | $0.00695 |
| Opus 5.5 | $0.00040 | $0.00278 |
| Sonnet 5.5 | $0.00020 | $0.00139 |
| Haiku 4.5 | $0.00010 | $0.00069 |
Grade A, and why
cross-model-consult 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consult a peer
You are Claude. Codex and Gemini are available as independent, read-only engineering peers.
model-peer ask <codex|gemini> "<focused question>"
model-peer doctor # which peers are available here
When it is worth the wait
- before committing to an architecture, schema, or migration decision
- when a bug has outlived two of your own hypotheses
- security-sensitive work: authn/authz, sandboxing, input handling, secrets, crypto
- unfamiliar code, or a dependency whose behavior you are inferring
- an assumption you cannot cheaply verify by reading the code
- two approaches you cannot decide between — ask for the tradeoff, not the verdict
Do not consult for anything you can settle by reading the code. Every consultation is a real model call against the developer's account and takes tens of seconds.
How to ask
The peer starts in this working directory with read-only tools, so name files and symbols instead of pasting excerpts, and ask one focused question. A peer that has to guess at scope returns generic advice.
# good — scoped to a symbol, answerable from the repository
model-peer ask codex "In src/auth/session.ts, can refresh_token leave the old token valid if rotation fails midway?"
# bad — no scope
model-peer ask codex "review my auth code"
Pipe context in when the question is about something not on disk:
git diff main... | model-peer ask gemini "What breaks in production?"
The answer is advisory
Evaluate it before acting. Peers do not know this project's invariants, so advice that contradicts the rules in this repository is wrong here however sound it sounds in general.
When a peer materially changed your decision, say which model you asked and whether you took the advice. Never present a peer's output as your own conclusion.
Leave --depth at its default: each peer answers alone, and lengthening the chain
is a human's deliberate call. Above depth 1 the peer does not run anything — it
asks Model Peer for a second opinion and Model Peer performs the consultation —
but every hop still costs time and money. A model is never consulted twice in one
chain.
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 First seen · 70 lines · 99 tokens per session scan A ac8286ff4901
cross-model-consult is a skill published in the GitHub repository makedirectory/ModelPeer (1 stars, last pushed 2mo ago), licensed MIT. It adds 99 tokens to every session and 695 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 2026-08-31.
Other skills, from other repositories
folder-flattening
Verschachtelte Ordnerhierarchien in flache, maschinenlesbare Strukturen umbauen. Bash-basiert mit intelligenter Merge-Logik.
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)…
time-awareness
Use when a claude-timestamp system reminder or Codex hook context says how long a turn has run, that a tool call was slow, or that a conversation or project is resumed after a gap; when the user asks how long something took, when they started, or where their time went; and before writing a date into notes, memory, a…
timestamps
Configure claude-timestamp when the user asks to change timestamps, timezone, clock format, marker appearance, elapsed time, tool timing, summaries, history, or model-facing time notes.
cloudflare-tunnel-routes
Give any local port (Gradio, Streamlit, FastAPI, webhook receiver, dev server, Docker container) a permanent HTTPS URL on a domain the user owns - in one command, no deployment. Use when the user says "my Gradio share link keeps changing", "replace share=True with a permanent URL", "stable URL for localhost:7860"…
shell-scripting
A guide to writing Bash shell scripts, which automate command-line tasks on Linux and similar systems. It covers variables, arrays, conditions, loops, functions, and safer script structure.