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 skills/chichou/grapefruit/igfnpx skills add ChiChou/grapefruit --skill igfgit 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/skills/chichou/grapefruit/igf)<a href="https://agentmods.dev/skills/chichou/grapefruit/igf"><img src="https://agentmods.dev/badge/skills/chichou/grapefruit/igf.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 | $0.00051 | $0.02714 |
| Opus 5 | $0.00026 | $0.01357 |
| Sonnet 5 | $0.00010 | $0.00543 |
| Haiku 4.5 | $0.00005 | $0.00271 |
Grade A, and why
igf 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 — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IGF (Grapefruit) CLI Skill
You are a CLI tool for interacting with the igf (Grapefruit) dynamic instrumentation server. The server runs at http://localhost:31337 by default (port configurable via PORT env or --port flag).
Architecture
IGF has two communication layers:
- REST API (stateless) — HTTP endpoints for device enumeration, history queries, file transfers
- Socket.IO RPC (stateful) — WebSocket session for real-time agent control, requires an active Frida session
RPC calls go through Socket.IO: emit("rpc", namespace, method, args, callback).
The agent organizes methods by namespace (e.g., fs.ls, pins.start, classes.list).
How to Execute
Use the igf CLI directly. All commands follow the pattern:
igf <command> [subcommand] [args] [options]
Global Options
-H, --host <host>— Server host (default: localhost)-p, --port <port>— Server port (default: 31337)-h, --help— Show help
Session Options (for agent commands)
-d, --device <id>— Device ID (required)--platform <name>— Platform:droidorfruity(required)-b, --bundle <id>— Bundle ID (app mode)--pid <pid>— Process ID (daemon mode)-n, --name <name>— Process name (daemon mode)
Commands
Device & App Management
| Command | Description |
|---|---|
igf device list |
List connected Frida devices |
igf device apps <device> |
List apps on device |
igf device ps <device> |
List running processes |
igf device info <device> |
Device system parameters |
igf device kill <device> <pid> |
Kill a process |
igf version |
Frida & IGF versions |
Log Management
| Command | Description |
|---|---|
igf log hooks <device> <id> [--limit N] |
Query hook logs |
igf log crypto <device> <id> [--limit N] |
Query crypto logs |
igf log syslog <device> <id> |
Read syslog |
igf log agent <device> <id> |
Read agent log |
igf log clear <device> <id> |
Clear all logs |
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 · 314 lines · 51 tokens per session scan A 9830a49fb526
igf is a skill published in the GitHub repository ChiChou/grapefruit (1,380 stars, last pushed 23d ago), licensed MIT. It adds 51 tokens to every session and 2,714 once invoked, about $0.0003 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 skills, from other repositories
analyzing-ios-app-security-with-objection
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
analyzing-ios-app-security-with-objection
Performs runtime mobile security exploration of iOS applications using Objection, a Frida-powered toolkit that enables security testers to interact with app internals without jailbreaking. Use when assessing iOS app security posture, bypassing client-side protections, dumping keychain items, inspecting filesystem…
analyzing-ios-app-security-with-objection
使用基于 Frida 的工具包 Objection 对 iOS 应用程序进行运行时移动安全探测， 无需越狱即可与应用内部交互。适用于评估 iOS 应用安全态势、绕过客户端防护措施、 转储 Keychain 条目、检查文件系统存储以及评估运行时行为。当请求涉及 iOS 安全测试、 Objection 运行时分析、基于 Frida 的 iOS 评估或移动运行时探测时激活。.
reverse-engineering-ios-app-with-frida
Reverse engineers iOS applications using Frida dynamic instrumentation to understand internal logic, extract encryption keys, bypass security controls, and discover hidden functionality without source code access. Use when performing authorized iOS penetration testing, analyzing proprietary protocols, understanding…
analyzing-ios-app-security-with-objection
Runtime iOS app security testing with Objection (Frida): inspect keychain and filesystem data, explore app internals at runtime, and validate/bypass client-side protections during authorized mobile assessments.
exploiting-deeplink-vulnerabilities
Tests and exploits deep link (URL scheme and App Link) vulnerabilities in Android and iOS mobile applications to identify unauthorized access, data injection, intent hijacking, and redirect manipulation. Use when assessing mobile app attack surface through custom URI schemes, Android App Links, iOS Universal Links, or…