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/chanmeng666/femtech-radar/agents-mdgit clone --depth 1 https://github.com/ChanMeng666/femtech-radarWrote 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/chanmeng666/femtech-radar/agents-md)<a href="https://agentmods.dev/instructions/chanmeng666/femtech-radar/agents-md"><img src="https://agentmods.dev/badge/instructions/chanmeng666/femtech-radar/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 5.1 | $0.05304 | $0.05304 |
| Opus 5 | $0.02652 | $0.02652 |
| Sonnet 5 | $0.01061 | $0.01061 |
| Haiku 4.5 | $0.00530 | $0.00530 |
Grade A, and why
femtech-radar 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 5d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides project guidance to AI coding assistants (Claude Code, GitHub Copilot, Cursor, Codex, etc.) working with this repository. Read it before writing or changing any code.
Project Overview
femtech-radar — Agent-first FemTech intelligence: a three-unit scrape → curate → publish pipeline that turns the scattered firehose of women's-health & FemTech signal into a curated, deduplicated, ranked, subscribable weekly digest, built entirely on GitHub-native primitives plus a reusable MCP server.
- Primary language / stack: TypeScript (strict, ESM) on Node.js ≥ 20, pnpm monorepo
- Default branch:
master - Repository: https://github.com/ChanMeng666/femtech-radar (public)
- Live site: https://chanmeng666.github.io/femtech-radar/ · RSS: https://chanmeng666.github.io/femtech-radar/rss.xml · Per-section RSS:
/rss/<section>.xml(e.g./rss/industry.xml) - npm package:
@chanmeng666/femtech-radar-mcp(v0.4.1)
Status: all three units are built and live in production. The pipeline runs end-to-end: the weekly
workflow calls the published MCP server, curates a digest, opens a data PR, and the site auto-deploys.
All five sections (industry, research, opportunities, discussions, china) now have source
adapters and are collected by the weekly workflow. Deferred to a future version: ChatOps slash commands
and bilingual support.
The Three Units
Sources ─► ① MCP server ─► ② weekly gh aw workflow ─► data/YYYY-Www.json ─► ③ Astro site + RSS
(arXiv, (deterministic: (editorial judgment: (Interface ②, (reads data/, auto-
Google fetch/dedupe/ Copilot curates + single source deploys to Pages)
News) score) writes why_it_matters) of truth)
Core principle — determinism vs judgment. Unit ① does ONLY deterministic work (fetch, normalize,
dedupe, score) and is reusable/unit-tested. ALL editorial judgment (which items, the per-item
why_it_matters line, the weekly editor_note, cross-section dedup) lives in Unit ②'s Copilot agent.
Unit ③ is pure presentation and reads only committed data. Keep these responsibilities separate.
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.
- 5d ago First seen · 207 lines · 5,304 tokens per session scan A c885b4a63361
femtech-radar AGENTS.md is an instructions file published in the GitHub repository ChanMeng666/femtech-radar (0 stars, last pushed 5d ago), licensed MIT. It adds 5,304 tokens to every session, about $0.0265 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 2026-09-01.
Other instructions, from other repositories
ConsultMe CLAUDE.md
Claude Code instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.
ai-research-arm CLAUDE.md
Claude Code instructions for guzus/ai-research-arm, covering claude.md, project overview, core pipeline architecture, key components and scripts (scripts/).
shipproof AGENTS.md
AGENTS.md instructions for kingggg5/shipproof, covering agents.md, what this repository is, non-negotiable rules, verify before declaring done and where things live.
KARIMO CLAUDE.md
Instructions for opensesh/KARIMO, covering karimo source repository rules, release protocol (mandatory), preferred method: release script, manual release checklist (if not using script) and critical: never move tags after release.
testivai-oss CLAUDE.md
Claude Code instructions for testivai/testivai-oss, covering testivai-oss — claude code guide, repo layout, package manager, common commands and architecture — how the oss lane works.
issueforge CLAUDE.md
Claude Code instructions for vietnamesekid/issueforge, covering issueforge, commands, the one rule enforced mechanically, where new code goes and typescript rules that bite.