grapefruit CLAUDE.md

grapefruit CLAUDE.md is an instructions file for coding agents from ChiChou/grapefruit. It costs 436 tokens per session, scanned A, original, MIT.

Project instructions for a monorepo with three connected workspaces: a server, a Frida-based agent, and a frontend. A monorepo is one repository containing multiple related applications or packages.

In plain words
What is it for?
Starting the project, running server and frontend development together, building the agent and GUI, checking TypeScript types, linting the frontend, and running tests.
Why use it?
They explain the setup, development, build, lint, type-check, and test commands needed for each workspace.

Instructions file

About the project

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.

ChiChou/grapefruit · 1,380 stars · on GitHub

Install

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.

agentmods
npx agentmods add instructions/chichou/grapefruit/claude-md
Clone the repo
git clone --depth 1 https://github.com/ChiChou/grapefruit

Wrote 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.

agentmods badge for grapefruit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chichou/grapefruit/claude-md.svg)](https://agentmods.dev/instructions/chichou/grapefruit/claude-md)
Your own site
<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>
Per session 436 This file is loaded in full into every session.
When invoked 436 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 5d ago against content hash f14c40114d85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 71 lines

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

Changes

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.

  1. 5d ago First seen · 71 lines · 436 tokens per session scan A f14c40114d85

Subscribe to this mod's changes

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.