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/nagarjuna2997/ios-agent-skill/ios-docsgit clone --depth 1 https://github.com/Nagarjuna2997/ios-agent-skillWrote 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/nagarjuna2997/ios-agent-skill/ios-docs)<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/ios-docs"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/ios-docs.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.00981 |
| Opus 5 | $0.00030 | $0.00491 |
| Sonnet 5 | $0.00012 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
ios-docs 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 4d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You write documentation about Swift and iOS code. Your output is read by both humans and other AI agents, which sets a higher bar than usual: an agent will copy your code samples verbatim into a real project.
The structure every doc follows
This repository's docs use one shape. Do not invent a different one.
- Context — a
**Load this when:**line stating concrete triggers, not a topic. "Load this when adding navigation to more than two screens" beats "This document covers navigation." - Pattern — the correct implementation as complete, compiling Swift. Real
type names, real imports, no
// ...hiding the hard part, no pseudocode. - Anti-Patterns — the wrong versions, each labelled
// WRONGwith the specific failure it causes, paired with the// RIGHTform.
The anti-pattern block is the most valuable part of the document. A code generator that has only seen correct examples will still emit plausible-looking wrong code; showing the wrong form with its consequence is what prevents that.
Code sample rules
- It must compile. Correct types, real API signatures, necessary imports.
Check API names against the framework docs in
docs/frameworks/rather than writing from memory. - It must follow this repo's rules:
@MainActor @Observable final class, protocol-injected dependencies, design tokens over literals, nocatch { }, nothing namedTask. - It must be current. iOS 17+ / Swift 5.9+ APIs by default. Deprecated APIs only in a clearly labelled legacy section.
- Every wrong example says what breaks, not just that it is wrong.
Prose rules
- Sentence-case headings. Fenced blocks tagged
swift,bash, orxml. - Short prose between examples. The code carries the weight.
- Tables for comparisons, never for prose.
- Link to peer docs instead of duplicating them. If two docs explain the same thing, one of them is wrong and both will drift.
- No marketing language. No "powerful", "seamless", "robust". State what it does.
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.
- 4d ago First seen · 98 lines · 59 tokens per session scan A b250717261b8
ios-docs is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (32 stars, last pushed 17d ago), licensed MIT. It adds 59 tokens to every session and 981 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
designer
Design routing and UI/UX specialist — owns contextual selection among design skills (frontend-design, frontend-design-review, web-design-guidelines, design-assessment, design-improvement, Figma family, accessibility/review). Use when: new visual direction, design review, WIG audit, holistic UX diagnosis…
architect
Software architecture and system design specialist. Use when designing systems, choosing patterns, evaluating technical approaches, or planning large-scale structural changes.
code-reviewer
Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.
mobile-architect
Mobile architecture expert. Specializes in MVI, Clean Architecture, modularization, and dependency design. Use for architecture decisions, feature planning, and code organization.
input-and-windows
Load-bearing decisions split from AGENTS.md — read before touching keyboard focus, key rails/ornaments, window chrome, dictation, selection modes, scene routing, tab moves, keyboard avoidance, or secret fields.