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/miuuyy/clew/agents-mdgit clone --depth 1 https://github.com/miuuyy/ClewWrote 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/miuuyy/clew/agents-md)<a href="https://agentmods.dev/instructions/miuuyy/clew/agents-md"><img src="https://agentmods.dev/badge/instructions/miuuyy/clew/agents-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 | $0.00633 | $0.00633 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
Clew AGENTS.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 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.
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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clew Codex Context
This file is the repository-specific context for Codex-style coding agents working in Clew.
The global hardmode contract still applies. This file adds project truth, architecture boundaries, and workflow expectations specific to Clew.
Read first
Before changing the product, read:
What Clew is
Product identity lives in docs/agents/PROJECT_CONTEXT.md. Read it before making product-shape changes.
Core product invariants
These are non-negotiable:
- The graph is the center of truth.
- AI must not silently mutate the graph.
- Accepted graph changes must stay reversible through snapshots.
- The UI must remain graph-first instead of dashboard-first.
- Local
mainand hosted product surfaces stay separate in emphasis.
If a change weakens any of those, it is a regression even if it looks convenient.
Engineering stance
- Prefer explicit boundaries over fast hacks.
- Keep model I/O inside visible contracts.
- Prefer fail-closed over fake success.
- Do not add hidden semantic routing or silent fallback behavior.
- Build for long-term clarity, not one seed graph or one happy-path demo.
Frontend stance
- The graph is the main surface, not decoration.
- Overlays must support the graph instead of replacing it.
- Avoid admin-dashboard vibes unless the user benefit is obvious.
- Portfolio-quality UI matters because product perception matters here.
Backend stance
- The repository and snapshot layer are first-class.
- Proposal validation matters more than “the model probably meant well”.
- If a provider or planner cannot satisfy a contract, reject explicitly.
- Side effects should remain legible through routes, repository, contracts, and traces.
Local commands
Start local dev:
./scripts/dev.sh
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 · 113 lines · 633 tokens per session scan A cd5142bbb2f4
Clew AGENTS.md is an instructions file published in the GitHub repository miuuyy/Clew (165 stars, last pushed 20d ago), licensed MIT. It adds 633 tokens to every session, about $0.0032 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
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
textbook-to-note CLAUDE.md
Instructions for drpwchen/textbook-to-note, covering claude.md — which audience are you?, working on this repo, spec before code, how much ceremony — decide before you start and the commit guard.
vault-cortex AGENTS.md
AGENTS.md instructions for aliasunder/vault-cortex, covering agents.md, what this project is, structure, module layering and logging.
ariadne AGENTS.md
Instructions for pariyar07/ariadne, covering ariadne — agent instructions, what this repo contains, how skills are structured, routing and rules.
second-brain-starter-kit AGENTS.md
AGENTS.md instructions for tonydzi/second-brain-starter-kit, covering agents.md — working in this repo, what this repo is, layout, how to verify a change and conventions.