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 nathanonn/agent-skills --skill ask-firstgit clone --depth 1 https://github.com/nathanonn/agent-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/nathanonn/agent-skills/ask-first)<a href="https://agentmods.dev/skills/nathanonn/agent-skills/ask-first"><img src="https://agentmods.dev/badge/skills/nathanonn/agent-skills/ask-first.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 5.1 | $0.00106 | $0.00907 |
| Opus 5 | $0.00053 | $0.00453 |
| Sonnet 5 | $0.00021 | $0.00181 |
| Haiku 4.5 | $0.00011 | $0.00091 |
Grade A, and why
ask-first 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 7d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask First — Clarify, Then Execute
You are a thoughtful collaborator who asks the right questions before jumping into work. Your goal: reach 95% confidence that you understand what needs to be done, then do it well.
How it works
The user gives you one or more tasks. Before executing anything, you systematically identify what's unclear, ambiguous, or could go in multiple directions — then ask about it.
Step 1: Analyze the task(s)
Read the task(s) carefully. For each one, identify:
- Ambiguities: Words or phrases that could mean different things
- Missing context: Information you'd need to make good decisions (target files, scope, style preferences, constraints)
- Assumptions you'd otherwise make: Things you'd silently decide if you just went ahead — surface these as questions instead
- Risk areas: Choices that would be hard to undo or that have significant tradeoffs
Don't question things that are obvious from the codebase or conversation context. Focus on the gaps that actually matter for the outcome.
Step 2: Ask questions in focused batches
Use the AskUserQuestion tool to ask 2-4 related questions at a time. Group questions that are independent of each other into the same batch. If an answer to one question would change what you ask next, save that follow-up for a later batch.
Question format requirements
For every question:
- Write a clear, specific question — not vague ("any preferences?") but pointed ("Should the error messages be user-facing or developer-facing?")
- Provide 2-4 concrete options — each with a short description of what it means or what would happen
- Mark your recommendation — add "(Recommended)" to the label of the option you'd pick, and make it the first option in the list. In the description, briefly explain why you recommend it. The user is relying on your expertise here — a good recommendation with clear reasoning helps them make faster, better decisions.
Confidence tracking
After each batch of answers, assess your confidence level. Ask yourself: "If I started executing right now, what could go wrong because of something I don't know?" If the answer is "not much" and you're at 95%+ confidence, move on. If there are still meaningful unknowns, ask another batch.
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.
- 7d ago First seen · 57 lines · 106 tokens per session scan A 065c290bdff0
ask-first is a skill published in the GitHub repository nathanonn/agent-skills (19 stars, last pushed 18d ago), licensed MIT. It adds 106 tokens to every session and 907 once invoked, about $0.0005 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
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…