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 skills/abdullah4ai/apple-developer-toolkit/asc-hitl-interactionnpx skills add Abdullah4AI/apple-developer-toolkit --skill asc-hitl-interactiongit clone --depth 1 https://github.com/Abdullah4AI/apple-developer-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/skills/abdullah4ai/apple-developer-toolkit/asc-hitl-interaction)<a href="https://agentmods.dev/skills/abdullah4ai/apple-developer-toolkit/asc-hitl-interaction"><img src="https://agentmods.dev/badge/skills/abdullah4ai/apple-developer-toolkit/asc-hitl-interaction.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 | $0.00034 | $0.01024 |
| Opus 5 | $0.00017 | $0.00512 |
| Sonnet 5 | $0.00007 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
asc-hitl-interaction 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASC Human-in-the-Loop Interaction
The terminal UI renders your questions with pickers based on the OPTIONS block format. Every question MUST include an OPTIONS block. Follow these patterns for all user-facing questions.
Core Rules
- Ask ONE question at a time — never dump multiple questions in a single message
- Always offer a suggestion — propose a value based on app context so the user can accept or tweak it
- Every question MUST use an OPTIONS block — the terminal renders these as navigable pickers
- If the user responds with "yes", "ok", "sure", "y", or similar — use your suggested value
- If the user responds with "Use your best judgment for this and all remaining fields" — enter auto mode (see below)
- Keep questions concise — one or two sentences max, then the OPTIONS block
Suggestion Fields (description, keywords, copyright, what's new, etc.)
When you have a suggested value, present it as the first option. Always include a text-entry option so the user can type a custom value.
Format:
**Description**: I'd suggest:
> "Your suggested description text here."
[OPTIONS]
- Use this suggestion | Accept the suggested description
- Enter my own | [INPUT] Type a custom value
[/OPTIONS]
Another example:
**Copyright**: I'd suggest: 2026 Mohammed Al-Quraini
[OPTIONS]
- Use this suggestion | Accept the suggested copyright
- Enter my own | [INPUT] Type a custom value
[/OPTIONS]
Rules:
- Show your suggestion ABOVE the OPTIONS block as a quote or inline text
- First option is always "Use this suggestion" (or a short label of the value if it's brief)
- Text-entry options MUST have
[INPUT]at the start of their description — this tells the terminal to show a text input prompt - The UI appends "Let AI decide" and "AI decides all" automatically — do NOT add them
Fixed-Option Fields (category, age rating, content rights, etc.)
When a field has a fixed set of valid values, list all valid values as options.
Format:
What age rating fits your app? This app has no objectionable content.
[OPTIONS]
- 4+ | No objectionable content (recommended)
- 9+ | Mild cartoon or fantasy violence
- 12+ | Infrequent mild language, simulated gambling
- 17+ | Frequent intense violence, mature themes
[/OPTIONS]
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 · 124 lines · 34 tokens per session scan A 1ca62fb90a07
asc-hitl-interaction is a skill published in the GitHub repository Abdullah4AI/apple-developer-toolkit (10 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,024 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…