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 instructions/ajevans99/swift-mcp-toolkit/agents-mdgit clone --depth 1 https://github.com/ajevans99/swift-mcp-toolkitWrote 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/ajevans99/swift-mcp-toolkit/agents-md)<a href="https://agentmods.dev/instructions/ajevans99/swift-mcp-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/ajevans99/swift-mcp-toolkit/agents-md.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 | $0.00365 | $0.00365 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
swift-mcp-toolkit 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 5d 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
AGENTS.md
This repository uses a standard Swift project template. These are the rules and expectations for any AI agents working inside this repo.
Language & Concurrency
- All code must be written in Swift (Swift 6+).
- Use structured concurrency: prefer
async/awaitandactors. - Do not introduce completion handlers, GCD, or callbacks unless absolutely required by an API.
Formatting & Linting
- Run
make formatbefore committing. This auto-formats code withswift-format. - Run
make lintto check lint errors not auto-fixed by the formatter. - Code must compile and pass both formatting and lint checks before merging.
Testing
- Use Swift Testing (
import Testinginstead of XCTest). - Every new public function should include at least one test.
- Async code should be tested with
@Test func ... async throws. - Keep tests small and focused, unless an integration test is explicitly needed.
- Use
swift testto run all tests and ensure they pass before merging.
Documentation & Examples
- Add doc comments (
///) for all public APIs. - Keep README code examples in sync with the current target/module name.
- Update import examples:
import <TargetName>. - Use minimal imports, for example, avoid
import Foundationunless necessary.
Security & Safety
- Always handle thrown errors explicitly.
- Avoid force unwraps (
!) or unchecked casts. - Use type-safe APIs whenever possible.
Agent Behavior
- Do not scaffold entire applications unless explicitly asked.
- Prefer to make small, precise changes that align with these rules.
- When suggesting alternatives, explain trade-offs clearly.
- Always produce code that builds and passes tests locally.
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.
- 5d ago First seen · 59 lines · 365 tokens per session scan A dccaa46e1fd4
swift-mcp-toolkit AGENTS.md is an instructions file published in the GitHub repository ajevans99/swift-mcp-toolkit (11 stars, last pushed 2mo ago), licensed MIT. It adds 365 tokens to every session, about $0.0018 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 2026-08-31.
Other instructions, from other repositories
swift-secp256k1 AGENTS.md
AGENTS.md instructions for 21-DOT-DEV/swift-secp256k1, covering agents.md (swift-secp256k1), commands, non-obvious patterns, code style and boundaries.
droidconKeKotlin AGENTS.md
AGENTS.md instructions for droidconKE/droidconKeKotlin, covering agents.md, commands, module layout, stack and conventions.
kormium AGENTS.md
AGENTS.md instructions for kormium/kormium, covering kormium for ai agents, mental model (read this first), define a schema, connect and inspect the sql without running it.
compose-android-template CLAUDE.md
Claude Code instructions for ashtanko/compose-android-template, a project described as: 📱 A simple GitHub template to quickly set up an Android project using Kotlin and Jetpack Compose, getting you up and running in just seconds. Perfect for starting new apps with modern Android UI.
xtool CLAUDE.md
Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.
skills CLAUDE.md
Claude Code instructions for chrisbanes/skills, a project described as: Skills for Kotlin, Jetpack Compose, and Android development.