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 cyuanxv/agent-cockpit --skill clarify-questiongit clone --depth 1 https://github.com/cyuanxv/agent-cockpitWrote 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/cyuanxv/agent-cockpit/clarify-question)<a href="https://agentmods.dev/skills/cyuanxv/agent-cockpit/clarify-question"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/clarify-question/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/cyuanxv/agent-cockpit/clarify-question"><img src="https://agentmods.dev/badge/skills/cyuanxv/agent-cockpit/clarify-question.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 | $0.00038 | $0.01165 |
| Opus 5 | $0.00019 | $0.00583 |
| Sonnet 5 | $0.00008 | $0.00233 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
clarify-question 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 9d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clarify Question
Use this skill when a request reaches Level 3 under
method/clarification-policy.md, when the user explicitly asks to refine a
question, or when a task must become a self-contained handoff.
Role
Your job is to discover the smallest set of user decisions that materially changes the work. Ask about goals and tradeoffs; investigate technical details yourself. Once the request is clear, produce a precise handoff prompt.
Do not execute the original task while running this skill unless the user explicitly switches to execution. Do not turn clarification into authorization.
Step 0: Load The Task Profile
Follow method/profile-context.md before deciding what the user may need help
clarifying:
- Read the current conversation.
- Load the configured base profile and only relevant Markdown memory.
- Separate confirmed preferences from agent inference.
- Record source, freshness, and confidence for conclusions that affect the questions.
- If sources conflict, follow the documented precedence and expose the conflict.
No profile entry is evidence that the user is unfamiliar with a domain. Upgrade only when there is a concrete hidden choice that could change the result.
Four-Level Boundary
- Level 1: execute directly. Do not invoke this skill.
- Level 2: state one key reversible assumption, then continue without a full clarification round.
- Level 3: explain why a decision matters, then ask 1-3 concise questions.
- Level 4: stop the side effect and request explicit authorization. This skill may clarify the target or scope, but its output is never authorization.
When more than one rule matches, the highest valid level wins.
Ambiguity Checklist
- Real goal: what decision or action is this meant to support?
- Scope: time, geography, audience, quantity, platform, version, or budget.
- Input materials: files, links, data, examples, screenshots, or prior decisions.
- Output shape: short answer, report, checklist, code change, plan, script, or handoff.
- Success criteria: what counts as done?
- Risk boundaries: publishing, spending money, account actions, destructive edits, private data, or external messages.
- Freshness: whether facts, prices, laws, APIs, product features, or policies need current verification.
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.
- 9d ago First seen · 136 lines · 38 tokens per session scan A 9ff7e07de0ae
clarify-question is a skill published in the GitHub repository cyuanxv/agent-cockpit (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,165 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
skillgrade-graders
Authors deterministic and LLM rubric graders for skillgrade evaluations. Use when creating scoring scripts, writing evaluation rubrics, or combining multiple graders with weighted scoring. Don't use for setting up eval pipelines, configuring eval.yaml defaults, or general test writing.
angular-modern-apis
Guidelines for using modern Angular APIs (signals, inject, control flow).
superlint
This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.
skillgrade-setup
Sets up and runs skillgrade evaluation pipelines for Agent Skills. Use when initializing eval configurations, running trials, reviewing results, or integrating with CI. Don't use for writing grader scripts, general test authoring, or non-agentic documentation.
self-improvement
บันทึกการเรียนรู้ ข้อผิดพลาด และการแก้ไขเพื่อการปรับปรุงอย่างต่อเนื่อง ใช้เมื่อ: (1) คำสั่งหรือการทำงานล้มเหลว (2) ผู้ใช้แก้ไขข้อมูล (3) ผู้ใช้ร้องขอความสามารถที่ไม่มี (4) API หรือเครื่องมือภายนอกล้มเหลว (5) พบแนวทางที่ดีกว่าสำหรับงานที่ทำซ้ำ หรือต้องการทบทวนการเรียนรู้ก่อนเริ่มงานสำคัญ.
rust-testing
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.