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/izzoa/polyrouter/claude-mdgit clone --depth 1 https://github.com/izzoa/polyrouterWhat 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 | $0.03402 | $0.03402 |
| Opus 5 | $0.01701 | $0.01701 |
| Sonnet 5 | $0.00680 | $0.00680 |
| Haiku 4.5 | $0.00340 | $0.00340 |
Grade A, and why
polyrouter CLAUDE.md 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 · 114 lines · 3,402 tokens per session scan A c91700fd40b1
polyrouter CLAUDE.md is an instructions file published in the GitHub repository izzoa/polyrouter (22 stars, last pushed 3d ago), licensed AGPL-3.0. It adds 3,402 tokens to every session, about $0.0170 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 2026-08-30.
Other instructions, from other repositories
nexu AGENTS.md
Instructions for nexu-io/nexu, covering agents.md, repo overview, project overview, commands and branch model.
gitmesh array.instructions.md
Instructions for LF-Decentralized-Trust-labs/gitmesh, a project described as: GitMesh: Policy-as-Code Engine for Open Source AI Agent Orchestration.
remnote-mcp-server AGENTS.md
Instructions for robert7/remnote-mcp-server, covering agents.md, repo role, companion repos (sibling dirs), contract map (current) and external mcp tool surface (17).
hermes-ai-team AGENTS.md
Instructions for smfworks/hermes-ai-team, covering mission, non-negotiable values (mirror docs/00-philosophy.md), how to consume this repo, working conventions and definition of done (for the phases in this repo).
Shiori-v1 AGENTS.md
Instructions for kaorii-ako/Shiori-v1, covering shiori — codex guide, commands, install all deps (root + client + server), dev (runs both client :5173 and server :3001) and client only.
pocketpaw AGENTS.md
Instructions for pocketpaw/pocketpaw, covering agents.md, agent identity, supported backends, capabilities and file system.