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/ginoleeswan/hero/claude-mdgit clone --depth 1 https://github.com/ginoleeswan/heroWrote 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/ginoleeswan/hero/claude-md)<a href="https://agentmods.dev/instructions/ginoleeswan/hero/claude-md"><img src="https://agentmods.dev/badge/instructions/ginoleeswan/hero/claude-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 | $0.05246 | $0.05246 |
| Opus 5 | $0.02623 | $0.02623 |
| Sonnet 5 | $0.01049 | $0.01049 |
| Haiku 4.5 | $0.00525 | $0.00525 |
Grade A, and why
hero CLAUDE.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 — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
Mythique — a superhero/villain encyclopedia app built with Expo SDK 56 / React Native.
Targets iOS, Android, and Web. (Repo slug + internal package dir stay hero; the product is branded Mythique.)
Documentation system
docs/README.md is the docs index — start there for any feature you don't
already know. Three layers, trust flows downward:
- This file — conventions, commands, hard rules.
docs/features/+docs/architecture/— evergreen as-shipped references per domain (Explore/Pulse, Arena, dailies, search, character page, profile, sharing/OG, auth/identity, push, platform/motion, admin, pipelines, houses). Kept current: if a PR changes a domain's behaviour, update its doc in the same PR.docs/superpowers/specs|plans/— ~170 dated historical design docs. The decision record, not the current truth; status lines in them go stale. Hidden from Grep via.ignore— read by explicit path only.
Package manager
Always use yarn. Never use npm or bun.
yarn install
yarn add <package>
yarn expo install <expo-package> # use for Expo-managed packages (pins correct version)
yarn start # dev server
yarn test:ci # run all tests once (CI mode)
Tech stack
| Concern | Library |
|---|---|
| Navigation | expo-router 4 (file-based) |
| Auth + DB | Supabase (@supabase/supabase-js) |
| Images | expo-image |
| Icons | @expo/vector-icons (Ionicons) |
| Fonts | @expo-google-fonts/nunito, @expo-google-fonts/righteous + custom Flame/FlameSans |
| Animations | react-native-reanimated 4 |
| Carousel | react-native-reanimated-carousel |
| Progress bars | react-native-progress |
| Card shape | react-native-figma-squircle + @react-native-masked-view/masked-view |
| Testing | jest-expo + @testing-library/react-native |
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 · 340 lines · 5,246 tokens per session scan A dbb3562e7079
hero CLAUDE.md is an instructions file published in the GitHub repository ginoleeswan/hero (59 stars, last pushed 4d ago), licensed MIT. It adds 5,246 tokens to every session, about $0.0262 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
tamagui AGENTS.md
AGENTS.md instructions for tamagui/tamagui, covering tamagui — agent operating contract, finish what you start, then merge it back, tamagui testing guide, running tests and kitchen sink tests.
lingo.dev CLAUDE.md
Claude Code instructions for lingodotdev/lingo.dev, covering extremely important instructions for claude, fyi, tools, testing and changesets.
tapflow AGENTS.md
AGENTS.md instructions for jo-duchan/tapflow, covering tapflow — agents.md (common rules), what, core value, two testing modes and why.
uniwind AGENTS.md
AGENTS.md instructions for uni-stack/uniwind, covering agent instructions and checks.
react-native-testing-library AGENTS.md
Instructions for callstack/react-native-testing-library: @testing-library/react-native is a TypeScript/Jest library for testing React Native components with user-focused testing patterns.
karakeep AGENTS.md
AGENTS.md instructions for karakeep-app/karakeep, covering karakeep project overview, project overview, project structure, applications (apps/) and packages (packages/).