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/swifttui/swift-tui/agents-mdgit clone --depth 1 https://github.com/SwiftTUI/swift-tuiWrote 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/swifttui/swift-tui/agents-md)<a href="https://agentmods.dev/instructions/swifttui/swift-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/swifttui/swift-tui/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 | $0.02410 | $0.02410 |
| Opus 5 | $0.01205 | $0.01205 |
| Sonnet 5 | $0.00482 | $0.00482 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
swift-tui 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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for Claude Code and other agentic assistants working in this
repository. Keep this file concise. The architecture documentation in
docs/ holds internal project notes. Developer-facing guides
live in the DocC catalogs under Sources/.
Build & Test Commands
bun run test # Repo gate: shared suite + policy checks
bun run test:all # Exhaustive checked-in primary-repo test surface
swiftly run swift build # Build all root-package targets
swiftly run swift test # Run root-package tests
swiftly run swift test --filter SwiftTUITests.SwiftUISurfaceTests # One test suite
swiftly run swift test --filter SwiftTUITests.SwiftUISurfaceTests/testName # One test
swift format format -i --configuration .swift-format.json Sources/ Tests/ # Format
Always run bun run test after changes that touch shared code, platform
products, or repository tooling. Make sure that it passes before you complete
the work. Example-package coverage lives in SwiftTUI/swift-tui-examples.
Do not run repo-local builds or tests with bare swift or xcrun swift — use
swiftly run swift ... so runs match the pinned toolchain. See
DEVELOPMENT.md
in the swift-tui-org coordination repository for the full toolchain, gate, and
release story.
Architecture (one-page summary)
SwiftTUIPrimitives -> SwiftTUIGraph -> SwiftTUICore -> SwiftTUIViews -> SwiftTUIRuntime
- SwiftTUIPrimitives — leaf vocabulary: inert value types only (geometry,
identity, style/color values, draw/layout metadata, the
Animatablemath). No engine, no render algorithms. Builds independently. Foundation-free. - SwiftTUIGraph — the reconciliation engine (the AttributeGraph analog).
It owns
ViewGraph/ResolvedNode, state slots, dependency tracking, invalidation planning, reuse gates, checkpoints, and entity routing. It also owns the runtime registries, the scheduler, and animation intent. Depends onSwiftTUIPrimitivesonly — the compiler enforces that graph code names no render type. Foundation-free. - SwiftTUICore — the render engine: measure/place/draw/raster/commit phases
and their typed products, extractors, style resolution, content engine. Consumes
the graph's
ResolvedNodesnapshots. It@_exported-imports Graph and Primitives, soimport SwiftTUICoreis unchanged. Terminal-IO-free. - SwiftTUIViews — the SwiftUI-shaped authoring surface (
View, controls, layout, state, focus, gestures).@_exported-imports Core so the publishedSwiftTUIViewsproduct is a self-sufficient authoring surface for external view libraries (SwiftTUICharts consumes exactly this). - SwiftTUIRuntime — the run loop, renderer, scenes, and host integration.
- SwiftTUI — the batteries-included convenience product. It re-exports the
combined terminal/WebHost runner and
SwiftTUIAnimatedImage. - SwiftTUICharts — chart and graph views. It ships from the peer repository
SwiftTUI/swift-tui-charts, composed on the publicSwiftTUIViewssurface.
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 · 185 lines · 2,410 tokens per session scan A 26abcb37f82b
swift-tui AGENTS.md is an instructions file published in the GitHub repository SwiftTUI/swift-tui (111 stars, last pushed yesterday), licensed MIT. It adds 2,410 tokens to every session, about $0.0120 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 instructions, from other repositories
Applite CLAUDE.md
Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.
skills-manager CLAUDE.md
Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.
starboard CLAUDE.md
Instructions for palamim/starboard, covering claude.md, commands, code style, architecture and non-obvious gotchas (not discoverable by reading the code).
skills-manager AGENTS.md
Instructions for yibie/skills-manager, covering repository agent instructions and ui and interaction work.
here-macos CLAUDE.md
Instructions for koalaauto/here-macos, covering here — ai assistant notes, architecture at a glance, prerequisites, build & run and always pass -quiet from an agent session.
swift-architecture-skill CLAUDE.md
Instructions for efremidze/swift-architecture-skill, covering swift architecture skill, project structure, how the skill works and key conventions.