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 MingyiSecLab/Mingyi-Atlas --skill structured-questionsgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/structured-questions)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/structured-questions"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/structured-questions/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/mingyiseclab/mingyi-atlas/structured-questions"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/structured-questions.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 | $0.00030 | $0.01133 |
| Opus 5 | $0.00015 | $0.00566 |
| Sonnet 5 | $0.00006 | $0.00227 |
| Haiku 4.5 | $0.00003 | $0.00113 |
Grade A, and why
structured-questions 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Operator Questions (ask_user_question)
The Soundwave interview has exactly one question channel:
ask_user_question— structured picker rendered in the CLI. For free-form dimensions (organization name, IP ranges, contact addresses) setallow_other=trueand the picker appends a free-text fallback the operator can type into.
There is no prose-question path. Every operator-facing question goes through this tool.
When to call ask_user_question
EVERY operator-facing question. There is no prose-question path. Provide
2–5 best-guess options for the dimension and always set allow_other=true
so the operator can override with a custom answer when none of your
predefined options fit.
Typical dimensions:
- Engagement type: External / Internal / Hybrid / Assumed-breach / Physical
- Attack class: Web / Cloud / AD / Mixed
- Scope window: Business hours / 24x7 / Custom
- Posture choices: OPSEC level (Loud / Quiet / Stealth)
- Confirmations: Two-option Yes / No after a derived assumption
- Phase selection: Multi-select over kill-chain phases (set
multi_select=true) - Free-form fields (organization / IP range / contact): still use the tool —
list 2–4 plausible guesses +
allow_other=true, the operator types the actual value via the Other fallback if your guesses miss.
The tool pauses the run while the operator picks, then resumes with the
chosen label (or list of labels for multi-select, or free text when the
operator chose Other). Treat the returned value as authoritative.
Habits (the typed tool signature already encodes the schema)
- Mark the most common option with a trailing
(Recommended)on itslabel - Never invent an
Otheroption yourself — setallow_other=trueand the picker appends a free-text fallback that returns the operator's text verbatim - For multi-select questions, set
multi_select=true; the tool returns the list of chosen labels (in selection order)
Examples
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 · 114 lines · 30 tokens per session scan A 86ea41fdacf9
structured-questions is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,133 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 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.