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/tools-for-agents/scout/agents-mdgit clone --depth 1 https://github.com/tools-for-agents/scoutWhat 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 | $0.00852 | $0.00852 |
| Opus 5 | $0.00426 | $0.00426 |
| Sonnet 5 | $0.00170 | $0.00170 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
scout 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 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — scout
🧭 The agent's web reader. Fetch a URL as clean, cached, searchable markdown (~90% smaller than the HTML). Clip the web, then distil into cortex. CLI + reading-room web view + MCP. Part of tools-for-agents.
Setup
node --version # 22+ required. Nothing to install.
npm test # = node --test
node src/cli.js fetch https://example.com
node src/cli.js serve --port 7950 # the reading room
npm run mcp # the MCP server, stdio
Zero runtime dependencies, and that is a hard rule. No dependencies in package.json, ever — this tool
reimplements readability rather than pull one in. Node 22+ gives you node:sqlite and a test runner.
| Env | For |
|---|---|
SCOUT_DB |
the cache database — always redirect this in tests |
SCOUT_PORT |
serve port (default 7950) |
SCOUT_MAX_BYTES |
fetch size cap |
SCOUT_CORTEX_URL |
optional cortex link-up |
The rules this repo is built on
1. Only the picture is evidence. Run iris against any UI
change and look at the shot before saying it works. Audit phone,tablet,desktop, both themes, --hover.
2. 🔑 A seeded gate is only reproducible from a CLEAN store. look-overview passed locally and failed in
CI because a dev .scout/cache.db had accumulated pages from earlier sessions that crowded the seeded
page out of heaviest — the local run was auditing different data. Always seed into a fresh db:
SCOUT_DB=/tmp/fresh/cache.db node scripts/seed.js
SCOUT_DB=/tmp/fresh/cache.db node src/cli.js serve --port 7951
3. Say [hidden] out loud. .toc-toggle[hidden] still rendered because a display: rule beats the
hidden attribute — the CSS must say .toc-toggle[hidden] { display: none }. This exact defect has now bitten
four repos in this kit.
4. Open the doors. The overview, the TOC and the recent strip are all behind something. Drive the page
with --pre and look. Still unopened: .ob-go, .sq-b, .rel-card.
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 · 69 lines · 852 tokens per session scan A d3c994184922
scout AGENTS.md is an instructions file published in the GitHub repository tools-for-agents/scout (0 stars, last pushed 28d ago), licensed MIT. It adds 852 tokens to every session, about $0.0043 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 instructions, from other repositories
cortex AGENTS.md
AGENTS.md instructions for tools-for-agents/cortex, covering agents.md — cortex, setup, the rules this repo is built on, tests and ci.
recall AGENTS.md
AGENTS.md instructions for tools-for-agents/recall, covering agents.md — recall, setup, the rules this repo is built on, tests and ci.
easy-notion-mcp CLAUDE.md
Instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
vetix AGENTS.md
Instructions for HuTa0kj/vetix, covering vetix — project map, repository layout, workflow, extension points and configuration.
skill-map CLAUDE.md
Instructions for crystian/skill-map: Pointer file. Claude Code (CLAUDE.md) and Codex (AGENTS.md) each pick up their own filename when they boot in this repo. Keeping CLAUDE.md as a one-line @AGENTS.md reference means the operating manual lives in a single file (AGENTS.md) without either tool falling back to defaults.…