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/agentx402-ai/agentscout/agents-mdgit clone --depth 1 https://github.com/agentx402-ai/agentscoutWrote 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/agentx402-ai/agentscout/agents-md)<a href="https://agentmods.dev/instructions/agentx402-ai/agentscout/agents-md"><img src="https://agentmods.dev/badge/instructions/agentx402-ai/agentscout/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 | $0.01472 | $0.01472 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
agentscout 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 3d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agent/contributor guide for this repo
Cross-tool agent instructions (the agents.md convention).
CLAUDE.md references this file; keep tool-specific notes there, shared truth here.
What this repo is
Open-source client surface for AgentScout — an agent-native, x402-paid web
read/extract/crawl service (service at api.agentx402.ai/v1/scout/*; the server is not in
this repo). npm-workspaces monorepo:
| Workspace | Package | What it is |
|---|---|---|
client/ |
@agentscout/client |
SDK — x402 payments, spend caps, read/extract/quote/crawl |
cli/ |
@agentscout/cli |
CLI + agentscout mcp MCP server (wraps the client) |
plugin/ |
(not published to npm) | Claude Code plugin wrapping the MCP server |
@agentx402-ai/core (shared x402/EIP-712 platform SDK) lives in its own repo
(agentx402-ai/core) and is consumed as a normal dependency.
Commands
npm ci # install (root; workspaces hoisted)
npm run build # client then cli (order matters — cli depends on client)
npm run typecheck # tsc --noEmit, both workspaces
npm test # builds client first (pretest), then client + cli suites (vitest)
npm run lint # biome ci . (CI gate — run before pushing)
npm run format # biome check --write .
npm --workspace client test -- spend-caps # one file, vitest filename filter
Run build before typecheck, not after. client/package.json points types at
./dist/index.d.ts, so cli's typecheck resolves @agentscout/client through the BUILT
client, not its source. Typechecking straight after editing client/src therefore reports
Cannot find module '@agentscout/client' — a false failure that points at the import rather than
at anything actually wrong. npm test is safe on its own (a pretest builds the client
first); a standalone npm run typecheck is not. CI only ever runs build-then-test, which is
why this never fires there. Working order: lint, build, typecheck, test.
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.
- 3d ago First seen · 98 lines · 1,472 tokens per session scan A 8d43a9776722
agentscout AGENTS.md is an instructions file published in the GitHub repository agentx402-ai/agentscout (0 stars, last pushed today), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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
Scrapegraph-ai AGENTS.md
Instructions for ScrapeGraphAI/Scrapegraph-ai, covering agents.md, 1. golden rule: everything goes to pre/beta, 1. always start from an up-to-date pre/beta, 2. commit your work and 3. push and open the pr against pre/beta.
AutomatiQ AGENTS.md
AGENTS.md instructions for StoneSteel27/AutomatiQ, covering agent guidelines, project map, daily commands, doctrine and config.
rdrr CLAUDE.md
Instructions for fkonovalov/rdrr, covering claude.md, what is this project?, project structure, common commands and code conventions.
hyalo CLAUDE.md
Claude Code instructions for ractive/hyalo, covering agents, documentation, dogfooding, rust and language server.
docpull AGENTS.md
AGENTS.md instructions for raintree-technology/docpull: DocPull is the open-source context dependency manager for AI agents. Its core contract is local-first, browser-free by default, reproducible, cited, and budget guarded.
webdown CLAUDE.md
Claude Code instructions for kelp/webdown, covering webdown development guide, working with claude, version management (semantic versioning), modern python development setup (python 3.10+) and build & testing commands.