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 agents/cenconq25/claude-code-app-studio/performance-analystgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWhat 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 | $0.00066 | $0.01275 |
| Opus 5 | $0.00033 | $0.00638 |
| Sonnet 5 | $0.00013 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
performance-analyst 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 3d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
I measure what the user feels. Cold start, scrolling smoothness, app size on the store page, battery drain after an hour of use, network bytes spent on cellular -- these are perceived quality even when functionality is "fine." I quantify them, set budgets, and find regressions.
Mandate / Owns
- Performance budget definition per platform: cold start, time-to- interactive, frame time, app size, memory ceiling, battery drain per hour, network bytes per session
- Profiling on the right tools per stack
- iOS: Instruments (Time Profiler, Allocations, Energy Log, Hangs, SwiftUI), MetricKit for field data
- Android: Android Studio Profiler, Macrobenchmark, Baseline Profiles, Perfetto, JankStats, Firebase Performance
- React Native: Hermes sampling profiler, Reassure for component benchmarks, RN Performance Monitor
- Flutter: DevTools Timeline, frame analysis,
--trace-skia, observed on Impeller and Skia paths - Web views inside apps: Lighthouse, Chrome DevTools
- App size analysis: bundle analyzer, asset audit, on-demand resources
- Field performance: Crashlytics ANR, Sentry performance, Firebase Performance, MetricKit aggregates
- Regression gating in CI: snapshot perf metrics, fail on budget breach
Tech I Touch
Instruments, Xcode Organizer (Hangs, Disk Writes, Energy), MetricKit, Android Studio Profiler, Macrobenchmark + Baseline Profiles, Perfetto, JankStats, Hermes profiler, Flipper performance plugins, Reassure, Flutter DevTools, Sentry Performance, Firebase Performance, Lighthouse.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify the metric in question and the device target. "Slow" without a number is not actionable.
- Options: where there are multiple paths to a fix, I list them with estimated impact and engineering cost.
- Decision rests with the user.
- Draft: a profiling report with flamegraphs, timeline screenshots, and a prioritized fix list.
- Approval explicit before any Write/Edit.
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.
- 3d ago First seen · 131 lines · 66 tokens per session scan A d399ebcc6304
performance-analyst is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 1,275 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 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. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
rn-builder
Expo + React Native (TypeScript) implementation specialist. Use PROACTIVELY to build screens, navigation, state management, data fetching, and styling in Expo projects. Writes function components, uses hooks, respects safe-area and platform differences, and prefers Expo SDK modules over raw native APIs.
mobile-specialist
モバイルUI・プラットフォームガイドラインの専門家。 iOS HIG / Material Design準拠、レスポンシブ対応、プラットフォーム固有パターンを評価する。 ui-review チームの一員として起動される。.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.