Grapefruit is an open-source suite for testing the security of iOS and Android mobile applications by instrumenting running apps and exposing their behavior through a web interface. Security researchers use it to inspect, intercept, and modify app functions, files, and cryptographic operations. Catalogue add-ons extend workflows for operating Grapefruit.
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/chichou/grapefruit/claude-mdgit clone --depth 1 https://github.com/ChiChou/grapefruitWrote 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/chichou/grapefruit/claude-md)<a href="https://agentmods.dev/instructions/chichou/grapefruit/claude-md"><img src="https://agentmods.dev/badge/instructions/chichou/grapefruit/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 | $0.00436 | $0.00436 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
grapefruit 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 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.
What it actually says
Monorepo with three workspaces:
- root (server),
agent/(Frida agent),gui/(frontend).
First-time setup
npm run setup # install all deps, build agent, gui, fetch/build WASM assets
Development
npm run dev # server with watch
npm run dev:both # tmux: server + gui dev
npm run dev:all # tmux/wt: agent watch + gui dev + server dev
Static checks
All code changes must pass the relevant checks before committing.
agent/ (Frida agent)
cd agent && npm run build # full build (agents + types)
cd agent && npm run type # generate/check agent types
gui/ (frontend)
cd gui && npm run lint # Oxlint
cd gui && npm exec tsgo -- --noEmit # type-check
cd gui && npm run build # full build
root (server)
npm exec tsgo -- --noEmit # type-check
npm test # run tests
Skills
Install skills for Claude Code:
igf setup # install to .claude/skills/ in current project
igf setup --global # install to ~/.claude/skills/ for all projects
Available skills:
/igf— CLI interface for the IGF server. Exposes all REST API and agent RPC./audit— Autonomous mobile security audit aligned with OWASP MASTG v2.
Code Style
Do not generate code splitter comments (or code dividers/dividers)
Prefer short symbol names. Do not repeat the module name in exported functions (e.g. ansi.toHtml not ansi.ansiToHtml). Drop noise words like "get", "create", "find" when the meaning is clear from context. Use import aliases to resolve name conflicts instead of making names longer.
git
Do not automatically commit unless I ask
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 · 71 lines · 436 tokens per session scan A f14c40114d85
grapefruit CLAUDE.md is an instructions file published in the GitHub repository ChiChou/grapefruit (1,380 stars, last pushed 24d ago), licensed MIT. It adds 436 tokens to every session, about $0.0022 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
FluidAudio copilot-instructions.md
Copilot instructions for FluidInference/FluidAudio, covering fluidaudio - agent development guide, build & test commands, architecture, critical rules and code style (swift-format config).
speech-swift AGENTS.md
AGENTS.md instructions for soniqo/speech-swift, covering agent instructions, communication style, workflow, running tests and benchmarks — sequential and memory-aware and git conventions.
maui-labs AGENTS.md
AGENTS.md instructions for dotnet/maui-labs, covering agent instructions, repository overview, products, technology stack and building.
maui-labs testing.instructions.md
Instructions for dotnet/maui-labs, covering testing guide, test framework, test projects, running tests and all tests.
AppClaw CLAUDE.md
Claude Code instructions for appclawhq/AppClaw, covering claude.md, what is appclaw?, build & run commands, architecture and entry point & cli modes (src/index.ts).
ios-simulator-skill CLAUDE.md
Instructions for conorluddy/ios-simulator-skill, covering claude.md - developer guide, project overview, project structure, architecture patterns and pattern 1: class-based script design.