agentmods.dev

ida-ios-analyze

ida-ios-analyze is a command for Claude Code from gyh20062008-commits/re-ios. It costs 16 tokens per session (461 once invoked), scanned A, original, MIT.

A command for optional IDA Pro-assisted analysis of an authorized iOS Mach-O binary or IDB file. IDA Pro is a reverse-engineering tool that helps inspect compiled programs and their functions, imports, strings, and symbols.

In plain words
What is it for?
Use it to inspect an iOS binary for functions, network libraries, URLs, authentication-related strings, and references to those strings.
Why use it?
It adds structured static analysis when an IDA MCP connection is available, while explaining when the required tool or active session is missing. It keeps the work within authorized analysis and does not perform attacks or bypass protections.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: positional $N argument.

Part of the ios-reverse-engineering plugin — 2 skills, 2 commands shipped together

not rated 1repo 2mo ago A scan 16 tokens original MIT

Good fit Use it to inspect an iOS binary for functions, network libraries, URLs, authentication-related strings, and references to those strings.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gyh20062008-commits/re-ios/ida-ios-analyze
View source ↗ gyh20062008-commits/re-ios
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.

Clone the repo
git clone --depth 1 https://github.com/gyh20062008-commits/re-ios

Made for: Claude Code.

Or install ios-reverse-engineering, the plugin that ships this one along with the rest of its 2 skills, 2 commands.

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 ida-ios-analyze

README.md
[![agentmods](https://agentmods.dev/badge/commands/gyh20062008-commits/re-ios/ida-ios-analyze/github.svg)](https://agentmods.dev/commands/gyh20062008-commits/re-ios/ida-ios-analyze)
Your own site
<a href="https://agentmods.dev/commands/gyh20062008-commits/re-ios/ida-ios-analyze"><img src="https://agentmods.dev/badge/commands/gyh20062008-commits/re-ios/ida-ios-analyze/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ida-ios-analyze

Your own site · 80×15
<a href="https://agentmods.dev/commands/gyh20062008-commits/re-ios/ida-ios-analyze"><img src="https://agentmods.dev/badge/commands/gyh20062008-commits/re-ios/ida-ios-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 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 $0.00016 $0.00461
Opus 5 $0.00008 $0.00230
Sonnet 5 $0.00003 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 11d ago against content hash c3ac9d5e887e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ida-ios-analyze 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 11d 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.

plugins/ios-reverse-engineering/commands/ida-ios-analyze.md · 47 lines

What it actually says

Optional IDA MCP iOS Analysis

Use the ida-assisted-ios-analysis skill.

Arguments:

  • $1: authorized Mach-O, IDB, or existing base analysis output directory.
  • $2: optional output directory. Default: ios_analysis_out/ida.

Safety boundary:

  • Authorized static analysis only.
  • Do not bypass FairPlay DRM, app encryption, certificate pinning, or legal restrictions.
  • Do not steal or use tokens, credentials, cookies, or sessions.
  • Do not call, fuzz, replay, probe, or attack discovered services.

Workflow:

  1. Run bin/ida-pro-mcp-check.
  2. If ida-pro-mcp is missing, explain that IDA-assisted analysis is unavailable and that the base iOS static analysis still works.
  3. Ask the user to open the target Mach-O or IDB in IDA if the MCP server requires an active IDA session.
  4. Use the MCP server named ida to confirm connectivity and loaded metadata.
  5. List functions, imports, exports, and strings.
  6. Search strings and symbols for URLSession, NSURLRequest, Alamofire, AFNetworking, Apollo, GraphQL, WebSocket, token, authorization, signature, hmac, nonce, and timestamp.
  7. For endpoint strings, inspect xrefs and map each xref to the containing function.
  8. Trace callers and callees for functions that reference endpoint or request-building evidence.
  9. Prefer the bundled scripts/ida_export_template.py when MCP can run IDAPython or when the user can run it inside IDA.
  10. Write ida-findings.md, ida-call-flow.md, and ida-network-evidence.json.

Suggested local checks:

bin/ida-pro-mcp-check

Suggested IDAPython template:

scripts/ida_export_template.py
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. 11d ago First seen · 47 lines · 16 tokens per session scan A c3ac9d5e887e

Subscribe to this mod's changes

ida-ios-analyze is a command published in the GitHub repository gyh20062008-commits/re-ios (1 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 461 once invoked, about $0.0001 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.

DebuggingMobile
Related

Other commands, from other repositories

flutter-build

Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.

affaan-m/ECC · 25 tokens

decompile

Decompile an Android APK/XAPK/JAR/AAR and analyze its structure.

CreditTone/android-reverse-engineering-skill · 15 tokens

safe-decompile

Safely fingerprint and decompile an Android artifact through the sandboxed MCP server.

salingnh/android-reverse-engineering-mcp · 16 tokens

proguard

Command "proguard" from getsentry/cli, covering examples, compute the uuid for a proguard/r8 mapping file, output as json (includes the file path) and important notes.

getsentry/cli · 0 tokens

debug

Debug Purchasely SDK issues — diagnose blank paywalls, frozen UI, purchase failures, and more.

Purchasely/Purchasely-AI-Plugin · 20 tokens

xcode-build-fix

Incrementally fix Xcode build and Swift compiler errors. Parse errors, explain issues, apply fixes, verify resolution.

OkminLee/everything-claude-code-ios · 23 tokens