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 instructions/watchandytw/multi-model-team/claude-mdgit clone --depth 1 https://github.com/WatchAndyTW/multi-model-teamWrote 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/instructions/watchandytw/multi-model-team/claude-md)<a href="https://agentmods.dev/instructions/watchandytw/multi-model-team/claude-md"><img src="https://agentmods.dev/badge/instructions/watchandytw/multi-model-team/claude-md.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 | $0.09818 | $0.09818 |
| Opus 5 | $0.04909 | $0.04909 |
| Sonnet 5 | $0.01964 | $0.01964 |
| Haiku 4.5 | $0.00982 | $0.00982 |
Grade B, and why
multi-model-team CLAUDE.md scanned grade B 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 4d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
top-level `statusLine`; the user adds the `statusLine` to their own `~/.claude/settings.json` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 541 lines · 9,818 tokens per session scan B 3499ca879432
multi-model-team CLAUDE.md is an instructions file published in the GitHub repository WatchAndyTW/multi-model-team (5 stars, last pushed 20d ago), with no licence file. It adds 9,818 tokens to every session, about $0.0491 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
agon AGENTS.md
Instructions for KERNlang/agon, covering agents.md — agon ai, using agon from codex, agon mode guide, team modes and tribunal and campfire options.
agent-skills CLAUDE.md
Claude Code instructions for simota/agent-skills, covering claude-skills, 構造, ルーティング（単一入口）, 規約 and 検査.
neo-skills AGENTS.md
AGENTS.md instructions for Benknightdark/neo-skills, covering neo-skills agents.md, 1. project overview, 2. commands, 3. workflow and 4. forbidden antipattern redlines.
agent-skills AGENTS.md
AGENTS.md instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.
agy-bridge CLAUDE.md
Instructions for sshahzaiib/agy-bridge: You have agy-bridge MCP tools that delegate heavy work to the Antigravity CLI (Gemini). Delegation keeps large content OUT of your context — only answers come back. Prefer delegating over doing it yourself when.
agy-plugin-cc CLAUDE.md
Instructions for Vit129/agy-plugin-cc, covering agy-plugin-cc — claude code guide, agent memory, global-first rule, project context (auto-loaded every session) and project summary.