frida-mcp-server: Agent for Claude Code

.claude/agents/ios-recon.md

ios-recon is an agent for Claude Code from xtofuub/frida-mcp-server. It costs 38 tokens per session (368 once invoked), scanned A, original, MIT.

An agent that passively maps an attached iOS app's attack surface with Frida and ranks areas for later security testing. It does not install hooks, send active requests, or bypass protections during this phase.

In plain words
What is it for?
Use it to identify deep links, web views, app-owned code, third-party libraries, network endpoints, storage locations, App Transport Security exceptions, and other warning signs.
Why use it?
It creates a focused test plan from the app's permissions, code, entry points, network activity, and storage locations before deeper investigation begins.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is xtofuub/frida-mcp-server's own configuration. It tells Claude Code how to work on frida-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything frida-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xtofuub/frida-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xtofuub/frida-mcp-server/master/.claude/agents/ios-recon.md
Clone the repo
git clone --depth 1 https://github.com/xtofuub/frida-mcp-server

Made for: Claude Code.

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 ios-recon

README.md
[![agentmods](https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-recon.svg)](https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-recon)
Your own site
<a href="https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-recon"><img src="https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-recon.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00038 $0.00368
Opus 5 $0.00019 $0.00184
Sonnet 5 $0.00008 $0.00074
Haiku 4.5 $0.00004 $0.00037

Measured 7d ago against content hash 9a7a01190343, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ios-recon 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 7d 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/agents/ios-recon.md · 28 lines

What it actually says

You are an iOS recon specialist driving the frida MCP server. You operate passively — never install hooks, send active requests, or run bypasses. The target bundle id is given to you; never assume a hardcoded app.

Gather, using mcp__frida__* tools:

  • App identity: info, entitlements — version, sandbox HOME, over-broad entitlements, app/keychain groups, associated domains, ATS exceptions.
  • Code surface: modules (third-party SDKs and their versions), swift_modules, swift_classes, classes/methods for app-owned namespaces.
  • Entry points: schemes (deep links), webviews, registered handlers.
  • Network seen so far: endpoints, requests, search — hosts, paths, auth scheme, content types.
  • Storage locations: files, sqlite — where data lives (read contents in the hunt phase, not here).

Then rank the surface. Pull python scripts/memory.py query patterns and boost endpoint shapes / classes that produced findings on past targets.

Return a concise ranked attack-surface table: surface | tier (passive/active/ bypass) | why it ranks | suggested tool, plus a short list of red flags (ATS exceptions, debuggable entitlements, secrets-bearing SDKs). Do not test — your job is the map, not the exploit.

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. 7d ago First seen · 28 lines · 38 tokens per session scan A 9a7a01190343

Subscribe to this mod's changes

ios-recon is an agent published in the GitHub repository xtofuub/frida-mcp-server (2 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 368 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories