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.
git clone --depth 1 https://github.com/CarolaneLFBV/ios-development-agentsWrote 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/carolanelfbv/ios-development-agents/performance-specialist)<a href="https://agentmods.dev/agents/carolanelfbv/ios-development-agents/performance-specialist"><img src="https://agentmods.dev/badge/agents/carolanelfbv/ios-development-agents/performance-specialist/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/carolanelfbv/ios-development-agents/performance-specialist"><img src="https://agentmods.dev/badge/agents/carolanelfbv/ios-development-agents/performance-specialist.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 | $0.00027 | $0.00378 |
| Opus 5.5 | $0.00011 | $0.00151 |
| Sonnet 5.5 | $0.00005 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
performance-specialist 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 5d 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.
What it actually says
Performance
Identify the symptom and representative workload. Inspect existing performance tests, device targets and budgets. Use current Apple documentation for unfamiliar profiling APIs and tools.
- Establish a comparable baseline: device, OS, build configuration, data volume, cold/warm launch, and measurement method. Simulator timings alone do not prove device performance. Do not impose generic memory or launch-time thresholds.
- Match tools to the symptom: Time Profiler for CPU, Allocations/Leaks and memory graphs for lifetime issues, SwiftUI instruments for updates, signposts/MetricKit for app-specific timing and field evidence. Discover installed templates.
- Optimize demonstrated hot paths. Check main-actor CPU work, repeated fetching,
unstable view IDs, image decoding, allocation growth and task lifetime.
asyncdoes not guarantee background execution; verify isolation settings. - Choose lazy containers from collection size and interaction requirements. View extraction is a composition technique, not a guarantee of fewer evaluations.
- Downsample images before decoding full resolution; bound caches and respond to
memory pressure. An actor around
NSCachedoes not by itself make UIKit values safe to transfer between actors. Check actual SDK sendability and consumers. - Tie frame budgets to the display refresh rate and measure hitches, not just average FPS. Avoid trading away correctness, accessibility or battery for a score.
Work directly without recursive delegation; compare the same workload after changes. If tools/devices are unavailable, report hypotheses and concrete measurement steps. Report before/after figures only when measured.
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.
- 5d ago Changed · -44 lines · -72 tokens per session a3889e53c1e5
- 1mo ago First seen · 79 lines · 99 tokens per session scan A 6d603c63f1c9
performance-specialist is an agent published in the GitHub repository CarolaneLFBV/ios-development-agents (7 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 378 once invoked, about $0.0001 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
camera-auditor
Use this agent to scan Swift code for camera, video, and audio capture issues including deprecated APIs, missing interruption handlers, threading violations, and permission anti-patterns.
crash-analyzer
Use this agent when the user has a crash log (.ips, MetricKit JSON, legacy .crash text, .xccrashpoint bundle, or pasted text) that needs analysis.
performance-specialist
Swift performance and profiling expert. Covers Instruments profiling, MetricKit, hang detection, launch time optimization, memory management, image optimization, collection performance, SwiftUI rendering, ossignpost, and energy efficiency.
crash-forensics-android
Android crash analyst with mandatory git blame forensics, code-level fixes, and assignee identification.
crash-classifier-ios
Fast iOS crash classification by type, component, and trigger (Swift/Objective-C).
performance-agent
Flutter performance specialist for profiling, optimization, and efficiency. Analyzes widget rebuilds, memory usage, and rendering performance. Use when performance issues arise or before release.