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 skills add memi-design/design-skills --skill ios-performance-debugginggit clone --depth 1 https://github.com/memi-design/design-skillsWrote 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/skills/memi-design/design-skills/ios-performance-debugging)<a href="https://agentmods.dev/skills/memi-design/design-skills/ios-performance-debugging"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/ios-performance-debugging/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/skills/memi-design/design-skills/ios-performance-debugging"><img src="https://agentmods.dev/badge/skills/memi-design/design-skills/ios-performance-debugging.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 | $0.00033 | $0.00276 |
| Opus 5.5 | $0.00013 | $0.00110 |
| Sonnet 5.5 | $0.00007 | $0.00055 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
ios-performance-debugging 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 2mo 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
iOS Performance Debugging
Workflow
- Define one reproducible user flow and one metric before changing code.
- Capture device, OS, build configuration, commit, data fixture, and baseline trace.
- Use the narrowest instrument: SwiftUI updates and hitches, Time Profiler, Allocations/Leaks, Network, Energy, or concurrency analysis.
- Correlate the trace to source. Do not optimize from intuition alone.
- Change one ownership, identity, layout, allocation, or scheduling cause at a time.
- Repeat the same flow and compare the same metric.
- Keep the trace, command, and before-after result in the handoff.
SwiftUI checks
- Stable identity in collections.
- Observation scoped to data the view actually reads.
- No expensive formatting, filtering, I/O, or object creation in
body. - Lazy containers used only where they fit the layout.
- Image decoding and resizing moved off the render-critical path.
- Navigation and sheet state represented by one source of truth.
Read references/trace-receipt.md before claiming a performance improvement.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 28 lines · 33 tokens per session scan A dc932b5ba084
ios-performance-debugging is a skill published in the GitHub repository memi-design/design-skills (7 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 276 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.
ios-performance-debugging compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ios-performance-debuggingmemi-design/design-skills | Skill | 7 | 1mo ago | MIT | A | 33 | Claude Code, Codex |
| gcd-operationsrusel95/ios-agent-skills | Skill | 13 | 24d ago | MIT | A | 165 | Claude Code |
| rn-metro-consoleAndrewDongminYoo/rn-agents-kit | Skill | 3 | 2d ago | Apache-2.0 | A | 72 | Claude Code |
| agent-dart-build-resolverKunanonJ/ai-skills-hub | Skill | 5 | 1mo ago | MIT | A | 55 | Claude Code, Codex |
| gspdev-auditjubscodes/get-shit-pretty | Skill | 55 | 5mo ago | MIT | A | 39 | Claude Code |
| gspdev-housekeepingjubscodes/get-shit-pretty | Skill | 55 | 5mo ago | MIT | A | 34 | Claude Code |
| gsp-doctorjubscodes/get-shit-pretty | Skill | 55 | 5mo ago | MIT | A | 0 | Claude Code |