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 arunveersingh/ai --skill day-01-ask-then-verifygit clone --depth 1 https://github.com/arunveersingh/aiWrote 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/arunveersingh/ai/day-01-ask-then-verify)<a href="https://agentmods.dev/skills/arunveersingh/ai/day-01-ask-then-verify"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-01-ask-then-verify/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/arunveersingh/ai/day-01-ask-then-verify"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/day-01-ask-then-verify.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 | $0.00048 | $0.00477 |
| Opus 5.5 | $0.00019 | $0.00191 |
| Sonnet 5.5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
ask-then-verify 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 23d 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
Ask, then verify
Confident wrongness is a false claim in the same calm voice as a true one. Fix it in two moves: ask so the answer is more likely correct or clearly UNKNOWN, then verify. Better asking cuts fiction; verification still decides what ships.
Paste Part A into any chat. Do Part B yourself. Swap brackets. Tighten or drop rules if you need to.
Part A — Ask (paste / adapt)
Answer this question: [YOUR QUESTION]
Rules:
1. Label each claim FACT or GUESS.
2. For every FACT, include a real source: a working URL, or the exact document title and where to look (section / page / heading).
3. If you cannot cite a real source, write UNKNOWN for that claim. Do not invent links, titles, names, dates, or numbers.
4. Prefer a quoted line or a URL over a vague summary.
Optional tighteners: ask for a checkable pointer ("Quote the line / give the URL that states X") instead of an open "what's the date of Y." Treat unlabeled "facts" as guesses until Part B.
Part B — Verify (you do this)
- Open the citation. Click the link or find the named doc. No citation, invented link/title, or UNKNOWN → do not paste the claim; stop or look yourself.
- Draft vs verified. Keep the reply as a draft. Ship only a verified version after at least one real check. Same window is fine; two buckets are not optional.
- Optional: After you score the draft (finished / detailed / correct-as-you-know), run one independent check (search or a second model). For claims that matter, name what would prove it wrong before you use it.
Done when: you either opened a real source and decided paste-ready / not, or you correctly stopped on UNKNOWN.
Lesson: Day 1 — Confident Wrongness
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.
- 23d ago First seen · 35 lines · 48 tokens per session scan A cef329a4de8b
ask-then-verify is a skill published in the GitHub repository arunveersingh/ai (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 48 tokens to every session and 477 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.