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 matiastripode/ios-agent-skills --skill ios-code-reviewergit clone --depth 1 https://github.com/matiastripode/ios-agent-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/matiastripode/ios-agent-skills/ios-code-reviewer)<a href="https://agentmods.dev/skills/matiastripode/ios-agent-skills/ios-code-reviewer"><img src="https://agentmods.dev/badge/skills/matiastripode/ios-agent-skills/ios-code-reviewer/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/matiastripode/ios-agent-skills/ios-code-reviewer"><img src="https://agentmods.dev/badge/skills/matiastripode/ios-agent-skills/ios-code-reviewer.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 | $0.00025 | $0.00455 |
| Opus 5.5 | $0.00010 | $0.00182 |
| Sonnet 5.5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
ios-code-reviewer 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 Code Reviewer
An agent skill for reviewing iOS/Swift code for quality, correctness, and App Store readiness.
When to Activate
- User asks to review iOS/Swift code
- User asks to check code before a PR or submission
- User runs
/ios-review - Files being reviewed are
.swift,.xib,.storyboard,Info.plist, or Xcode project files
Decision Tree
Is the code Swift?
├── YES
│ ├── Does it involve UI? → Check references/performance-checklist.md (main thread, cell reuse)
│ │ → Check references/accessibility.md (VoiceOver, Dynamic Type)
│ ├── Does it use closures, delegates, or timers? → Check references/memory-management.md
│ ├── Is it a public API or protocol? → Check references/api-design.md
│ ├── Is it preparing for App Store submission? → Check references/app-store-rejection.md
│ └── General review → Check all references as applicable
├── NO (Info.plist, project files, storyboards)
│ └── Check references/app-store-rejection.md for missing keys/configurations
Review Output Format
For each finding, report:
### [Severity] Category: Brief Description
- **File:** path/to/file.swift:line
- **Issue:** What is wrong
- **Fix:** How to fix it
- **Reference:** Which reference doc covers this
Severity levels: CRITICAL, WARNING, SUGGESTION
Reference Documents
references/memory-management.md- Retain cycles, ARC, delegate patternsreferences/api-design.md- Swift naming, protocols, error handlingreferences/performance-checklist.md- Main thread, cell reuse, image cachingreferences/app-store-rejection.md- Common rejection reasons and fixesreferences/accessibility.md- VoiceOver, Dynamic Type, tap targets
What ships with it
5 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 · 53 lines · 25 tokens per session scan A cf766cd68466
ios-code-reviewer is a skill published in the GitHub repository matiastripode/ios-agent-skills (2 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 455 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-code-reviewer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ios-code-reviewermatiastripode/ios-agent-skills | Skill | 2 | 7mo ago | MIT | A | 25 | Claude Code, Codex |
| app-store-reviewjacklandrin/OnlySwitch | Skill | 6.0k | yesterday | MIT | A | 76 | Claude Code, Codex |
| swift-concurrency-projacklandrin/OnlySwitch | Skill | 6.0k | yesterday | MIT | A | 35 | Codex |
| swiftui-protwostraws/SwiftUI-Agent-Skill | Skill | 6.5k | 11d ago | MIT | A | 36 | Claude Code, Codex |
| axiom-audit-cameraCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 39 | Codex |
| mobile-platform-offline-validateforcedotcom/sf-skills | Skill | 1.1k | 2d ago | Apache-2.0 | A | 207 | Claude Code |
| mobiai-review-codeArisGuimera/MobiAI-Core | Skill | 492 | 4d ago | MIT | A | 28 | Claude Code |