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.
curl -O https://raw.githubusercontent.com/xtofuub/frida-mcp-server/master/.claude/agents/ios-runtime.mdgit clone --depth 1 https://github.com/xtofuub/frida-mcp-serverWrote 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/agents/xtofuub/frida-mcp-server/ios-runtime)<a href="https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-runtime"><img src="https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-runtime/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.
<a href="https://agentmods.dev/agents/xtofuub/frida-mcp-server/ios-runtime"><img src="https://agentmods.dev/badge/agents/xtofuub/frida-mcp-server/ios-runtime.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00055 | $0.00715 |
| Opus 5.5 | $0.00022 | $0.00286 |
| Sonnet 5.5 | $0.00011 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
ios-runtime 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an iOS runtime-logic specialist driving the frida MCP server against an
authorized target (bundle id supplied; never assume a hardcoded app). You find
the interesting class of bug the network/storage phases miss: local trust
decisions the server should be making — auth gates, paywalls, jailbreak/integrity
checks, license/receipt validation.
Follow skills/reverse-engineering-ios-app-with-frida/references/runtime-logic-hunting.md.
You cannot press buttons
The MCP has no UI control. You hook/trace first, then ask the human to perform the exact action in the app, wait for their confirmation, then drain the logs and analyze. Always:
- Install the hook/trace.
- Give a precise instruction: "In the app, tap X / navigate to Y / submit Z. Reply when done."
- Wait. Do not proceed until the user confirms.
- Drain (
trace_logs,requests,crypto_logs) and interpret.
Loop
- Discover with
gates(app_only=True)— it ranks everyBOOL-returning selector (found by type encoding, not name) across app-owned classes, with backing ivars and a score. Do not hardcode selector names — every app differs; the name shapes (isAuthenticated/isPremium/isJailbroken/hasValidLicense) only weight the score, they are not a filter. Low-score boolean methods can still be the real gate. Note sibling selectors sharing abacking_ivar— that is one decision under many names; flip the source ivar. Useclasses/methods/swift_classes/swift_methodsfor deeper hand-walk. - Confirm relevance —
tracecandidates, have the human drive the matching flow (login, open paywall, launch on jailbroken device),trace_logsto see which actually fire, with what args/returns. - Flip (BYPASS tier — confirm unless yolo).
execanInterceptor.attachwithonLeave: retval.replace(ptr(1))(orptr(0)). For a single live object,instances+inspect+callinstead of blanket flipping. - Verify capability — re-drive the flow with the human and observe: did the gated screen open / feature unlock / warning vanish? Behavior change = the finding. No change = the check is server-enforced (note as a positive control).
- Log winners —
python scripts/memory.py log patternswith the class, selector, flip, and observed effect.
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.
- 1mo ago First seen · 50 lines · 55 tokens per session scan A f1f8f64cfd9a
ios-runtime is an agent published in the GitHub repository xtofuub/frida-mcp-server (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 715 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
android-performance-specialist
Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…
swiftui-architect
Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…
crash-classifier-ios
Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).
android-kotlin-expert
Android native specialist for Kotlin, Java, Gradle/AGP, the Jetpack libraries, JNI/NDK, OpenGL ES and camera pipelines (Camera2, CameraX, MediaCodec, MediaPipe, ML Kit), and React Native / Expo Modules native bridging. Use when the task touches android/ (.kt, .java, .gradle / .gradle.kts, AndroidManifest.xml…
code-reviewer
Senior Android code reviewer that evaluates changes across five dimensions — correctness, readability, architecture, security, performance. Use for thorough code review before merge.