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/childrentime/reactuse/claude-mdgit clone --depth 1 https://github.com/childrentime/reactuseWhat 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 | $0.02515 | $0.02515 |
| Opus 5 | $0.01257 | $0.01257 |
| Sonnet 5 | $0.00503 | $0.00503 |
| Haiku 4.5 | $0.00251 | $0.00251 |
Grade A, and why
reactuse CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST https://dev.to/api/articles \ How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReactUse - Project Guidelines
Project Overview
ReactUse is a collection of React hooks (@reactuses/core). The website is built with Astro (packages/website-astro).
Development
pnpm install # install dependencies
pnpm lint # eslint
pnpm test # jest, via @reactuses/core
Generated API docs
packages/website-astro/api/{hook}-README{,-zhHans,-zhHant}.md are generated from each
hook's interface.ts by pnpm --filter @reactuses/core gend. The Astro site splices them
into every doc page at the %%API%% marker (src/plugins/remark-api-inject.mjs), and
packages/mcp reads them too.
If you change an interface.ts, re-run gend and commit the result. The remark plugin
drops the marker silently when a file is missing or stale, so the published API table just
keeps showing the old signature with no build error.
AI Agent System (.claude/)
This repo carries a small, Chromium-inspired AI agent system under .claude/ — sized for a
hooks library, not a 35M-line codebase. Map: .claude/README.md.
Engineering workflow (apply to any hook/code task):
- Understand first. Read the real source of the files you'll touch — and at least one similar existing hook — before writing. Don't infer behavior from names.
- Build, reusing what exists. This codebase has a shared util layer and strong conventions; reuse before writing. Browser APIs must be SSR-safe.
- Test. Jest, co-located
index.spec.ts(pnpm --filter @reactuses/core test <name>). - Verify.
pnpm lint+ tests green. Stay on task — no unrelated drive-by edits.
Where to look:
.claude/knowledge-base.md— task → file/utility router. Start here; it tells you which existing code already solves your task..claude/ai-policy.md— you own every line you ship; understand it before review.- Skills (auto-activate):
new-hook,hook-test,hook-docs,pr-description. - Commands:
/new-hook,/pre-pr,/pr-desc.
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 · 173 lines · 2,515 tokens per session scan A adc1b3aac240
reactuse CLAUDE.md is an instructions file published in the GitHub repository childrentime/reactuse (1,048 stars, last pushed 12d ago), licensed Unlicense. It adds 2,515 tokens to every session, about $0.0126 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
agent-skills AGENTS.md
Instructions for siberiacancode/agent-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.
agent-skills CLAUDE.md
Instructions for siberiacancode/agent-skills, a project described as: 🤖 ai skills.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.