Borrowing it
Nothing to install: this file belongs to TechHU-GS/cc-discipline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TechHU-GS/cc-discipline/main/.claude/skills/ask-me/SKILL.mdgit clone --depth 1 https://github.com/TechHU-GS/cc-disciplineWrote 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/techhu-gs/cc-discipline/ask-me)<a href="https://agentmods.dev/skills/techhu-gs/cc-discipline/ask-me"><img src="https://agentmods.dev/badge/skills/techhu-gs/cc-discipline/ask-me/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/techhu-gs/cc-discipline/ask-me"><img src="https://agentmods.dev/badge/skills/techhu-gs/cc-discipline/ask-me.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 | $0.00037 | $0.00936 |
| Opus 5.5 | $0.00015 | $0.00374 |
| Sonnet 5.5 | $0.00007 | $0.00187 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
ask-me 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask the user a question they can answer in one step.
This replaces two failures. One is a wall of text with the real question buried at the end. The other is a bare open question the user cannot answer, because the context needed to answer it is in your head, not theirs.
1. Decide what actually needs asking
- Topic. If the user gave arguments, that is the topic. Otherwise it is whatever decision is pending in the conversation: the thing you would otherwise ask in prose, or quietly guess.
- Settle what you can first. Read the file, run the command, check
docs/progress.mdanddocs/todo.md. Ask only what is left, which should be the user's preferences and direction, or facts only they know. A question whose answer is in the repo wastes the user's turn. - Nothing pending? If nothing is actually open, say so in one line and stop. Do not invent a question so that the skill has something to do.
2. Background first, in plain text, briefly
Write three to six lines before the question, covering only what the user needs in order to choose:
- what is already settled;
- where things are stuck, and why it is the user's call: a trade-off, a preference, a risk;
- anything you checked that changes the options, with
file:linewhen it helps.
Save the analysis of each option for that option's description. If the background runs past about six lines, you are explaining too much or asking too early.
3. Ask with AskUserQuestion
- Questions. Ask one to four per call, and only ones whose answer changes what you do next. Put related questions in the same call rather than drip-feeding them. Write them in the user's language.
- Options.
- Give two to four per question, and make them genuinely different.
- Do not add an "Other" option; the tool provides one.
- Put your recommendation first and mark it in the user's language, "（推荐）" or "(Recommended)". Its description says why in one sentence.
- If you have no basis for recommending one, say that in the background rather than marking one at random.
- Descriptions. Each option's description says what happens if it is chosen and what that costs. Do not restate the label.
- Header. At most 12 characters.
- multiSelect. Use it only when the choices combine, for example which items to include. An empty multi-select answer is ambiguous: ask again rather than assume.
- preview. Use it when the user needs to compare concrete artifacts: code, configuration, layouts. It works for single-select questions only.
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.
- 1mo ago First seen · 54 lines · 37 tokens per session scan A b8635eec4ff1
ask-me is a skill published in the GitHub repository TechHU-GS/cc-discipline (0 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 936 once invoked, about $0.0001 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 2026-09-28.
Other skills, from other repositories
create_note
Capture findings or context as a persistent note in the thoughts system.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
omh-morning-brief
This is a Hermes-native morning-brief workflow skill.
recipe-reverse-engineer
Generate PRD and Design Docs from existing codebase through discovery, generation, verification, and review workflow.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
documentation-criteria
Determines which of PRD, ADR, UI Spec, Design Doc, and Work Plan a change requires, and where each is stored. Use when deciding documentation scope, or when creating or reviewing a technical document.