Borrowing it
Nothing to install: this file belongs to sorunokoe/swift-kmp-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sorunokoe/swift-kmp-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/sorunokoe/swift-kmp-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/instructions/sorunokoe/swift-kmp-skill/agents-md)<a href="https://agentmods.dev/instructions/sorunokoe/swift-kmp-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/sorunokoe/swift-kmp-skill/agents-md/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/instructions/sorunokoe/swift-kmp-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/sorunokoe/swift-kmp-skill/agents-md.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 | $0.00675 | $0.00675 |
| Opus 5.5 | $0.00270 | $0.00270 |
| Sonnet 5.5 | $0.00135 | $0.00135 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
swift-kmp-skill AGENTS.md 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — swift-kmp
This file is for AI coding agents reading or contributing to this repository.
What This Repository Is
A structured AI coding skill for developers building Kotlin Multiplatform (KMP) apps with Swift/iOS native UI.
The core rule: Feature modules must never import the KMP framework (regardless of integration method).
They receive @Sendable closures with pure Swift types. Every KMP import lives
in one place — the bridge layer.
Repository Structure
SKILL.md ← ALWAYS load first — hard rules, cheatsheet, review checklist
references/
├── architecture.md ← 4-layer bridge model, iOS integration methods, module boundary rule
├── interactor-pattern.md ← Interactor template, @concurrent nonisolated, error handling
├── flow-bridging.md ← SkieSwiftFlow vs AsyncStream, leak-safe onTermination
└── type-mapping.md ← Kotlin sealed dispatch, KotlinThrowable, collections, Sendable
🔗 Compose Multiplatform ↔ SwiftUI (
UIViewControllerRepresentable, coordinator pattern, teardown) is covered by the companion swiftui-compose skill.
How to Apply This Skill
- Load
SKILL.md— this contains the hard rules and a review checklist - Check the Reference Router table in
SKILL.mdto identify which reference is needed - Load that one reference file only (loading all wastes tokens unnecessarily)
- Apply the patterns, then run the Review Checklist
Skill loading order
SKILL.md → references/architecture.md (if module boundary ownership is unclear)
→ references/<specific-topic>.md (for this task's API contract)
Key Invariants
When modifying any file in this repository:
- No project-specific names — use
YourKmpFramework,AppComponent, generic feature names - All code examples must be compilable — no pseudo-code without clear labeling
- Official doc links must be live — verify any URL you add
- Hard rules stay hard — never soften a ❌ rule without strong justification
- Transitional patterns stay labeled —
onEnum(of:)and@preconcurrency importare explicitly SKIE-era; keep migration notes
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 · 80 lines · 675 tokens per session scan A f32c5eb62e95
swift-kmp-skill AGENTS.md is an instructions file published in the GitHub repository sorunokoe/swift-kmp-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 675 tokens to every session, about $0.0027 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.
swift-kmp-skill AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| swift-kmp-skill AGENTS.mdsorunokoe/swift-kmp-skill | Instructions file | 5 | 4mo ago | MIT | A | 675 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |