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 skills add sambitcreate/Swift-Foundation-Models-Skills --skill apple-foundation-models-generation-tuninggit clone --depth 1 https://github.com/sambitcreate/Swift-Foundation-Models-SkillsWrote 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/skills/sambitcreate/swift-foundation-models-skills/apple-foundation-models-generation-tuning)<a href="https://agentmods.dev/skills/sambitcreate/swift-foundation-models-skills/apple-foundation-models-generation-tuning"><img src="https://agentmods.dev/badge/skills/sambitcreate/swift-foundation-models-skills/apple-foundation-models-generation-tuning/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/skills/sambitcreate/swift-foundation-models-skills/apple-foundation-models-generation-tuning"><img src="https://agentmods.dev/badge/skills/sambitcreate/swift-foundation-models-skills/apple-foundation-models-generation-tuning.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 | $0.00023 | $0.00196 |
| Opus 5 | $0.00012 | $0.00098 |
| Sonnet 5 | $0.00005 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
apple-foundation-models-generation-tuning 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 11d 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
Generation Tuning
Use when
- Working with generation tuning in your iOS/macOS project
- Implementing features related to generation tuning
- Debugging issues with generation tuning
Don't use when
- Just doing basic chat (use apple-foundation-models-session-patterns)
- Need structured output specifically (use apple-foundation-models-structured-generation)
Workflow
- Review the skill documentation
- Check references/guide.md for code examples
- Implement according to your use case
- Test with actual model interactions
Hard rules
- Follow Apple platform guidelines
- Handle errors gracefully
- Respect user privacy and data handling
References
See references/guide.md for code examples and repo file paths.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 36 lines · 23 tokens per session scan A da4b847571c0
apple-foundation-models-generation-tuning is a skill published in the GitHub repository sambitcreate/Swift-Foundation-Models-Skills (23 stars, last pushed 6mo ago), licensed MIT. It adds 23 tokens to every session and 196 once invoked, about $0.0001 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 skills, from other repositories
afm
Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR. Use when working on AFM CLI commands (afm, afm mlx, afm vision), OpenAI /v1/chat/completions and /v1/models behavior, streaming SSE, tool-calling…
apple-foundation-models-skill
Write, review, or integrate Apple's FoundationModels framework (iOS 26.0+, macOS 26.0+), including WWDC 2026 beta APIs (OSs 27.0+). Use for on-device generation, structured output, tool calling, streaming, prompt attachments, dynamic profiles, agentic orchestration, session properties, Private Cloud Compute, or custom…
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.