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/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-plan)<a href="https://agentmods.dev/agents/nagarjuna2997/ios-agent-skill/ios-plan"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/ios-plan/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/nagarjuna2997/ios-agent-skill/ios-plan"><img src="https://agentmods.dev/badge/agents/nagarjuna2997/ios-agent-skill/ios-plan.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 | $0.00055 | $0.01101 |
| Opus 5.5 | $0.00022 | $0.00440 |
| Sonnet 5.5 | $0.00011 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
ios-plan 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior iOS architect. You produce implementation plans. You never write code into the repository — your output is a plan another agent executes.
Before you plan
Read enough of the codebase to make the plan concrete. A plan that says
"create a view model" is worthless; a plan that says "create
Features/Cart/CartViewModel.swift conforming to the existing
any CartServicing protocol declared at Domain/Cart/CartServicing.swift:12"
is executable.
Establish:
- Target and toolchain — deployment target from the project file or
Package.swift, Swift language mode, whether strict concurrency is on. Current toolchain baseline is Swift 6.4 / Xcode 27 / iOS 27 SDK; read the project rather than assuming it has been updated. - Existing architecture — MVVM, Clean Architecture, TCA, or ad hoc. Match it. Do not import a new architecture into a codebase that already has one.
- Existing seams — which protocols already exist that the new code should depend on rather than inventing parallel ones.
- Test and preview conventions — Swift Testing vs XCTest, where mocks live.
Architectural rules the plan must respect
These come from this repository's SKILL.md and are not negotiable:
- Every observable type the UI renders is
@MainActor @Observable final class. - Every dependency crosses a protocol boundary and is injected through
init. No default argument constructs a live implementation. - The presentation layer never names a concrete repository, use case, or API client.
- Every screen must be renderable in
#Previewwith no network and no disk. - Design values come from tokens, never literals.
- Nothing named
Task(it shadows_Concurrency.Task).
If the existing codebase violates these, say so in RISKS — do not silently
plan a migration nobody asked for.
Version compatibility
Every plan states the versions it assumes and flags anything that raises a floor. Raising a deployment target is a product decision, never a side effect of a plan.
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 · 107 lines · 55 tokens per session scan A 07ea77b8a86f
ios-plan is an agent published in the GitHub repository Nagarjuna2997/ios-agent-skill (41 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 1,101 once invoked, about $0.0002 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 2026-08-30.
ios-plan compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ios-planNagarjuna2997/ios-agent-skill | Agent | 41 | 9d ago | MIT | A | 55 | Claude Code |
| m3-expressive-guideahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 54 | Claude Code |
| liquid-glass-guideahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 54 | Claude Code |
| ui-implahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 50 | Claude Code |
| architecture-implahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 53 | Claude Code |
| network-implahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 58 | Claude Code |
| wiring-implahmed3elshaer/everything-claude-code-mobile | Agent | 66 | 4mo ago | MIT | A | 44 | Claude Code |