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 akiotanaka847/qaio-desktop --skill answer-a-legal-questiongit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote 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/akiotanaka847/qaio-desktop/answer-a-legal-question)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/answer-a-legal-question"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/answer-a-legal-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/akiotanaka847/qaio-desktop/answer-a-legal-question"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/answer-a-legal-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 | $0.00066 | $0.01289 |
| Opus 5 | $0.00033 | $0.00645 |
| Sonnet 5 | $0.00013 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
answer-a-legal-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 12d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer a Legal Question
When to use
- "do I need an NDA with investors?" - typically no, pitch-stage investors refuse.
- "do I need a DPA with {vendor}?" - depends on data + region.
- "does GDPR apply to me?" - depends on EU visitors/customers + data.
- "can I use this customer logo on my landing page?" - depends on MSA marketing rights clause.
- "do I need to file an 83(b)?" - probably yes, within 30 days of stock issuance. Hard deadline.
- Any "do I need X?" or "does X apply?" fits short memo.
Steps
-
Read shared context. Load
legal-context.mdfor entity, data geography of current users, standing agreements, founder risk posture, escalation rules. Also read relevant prioradvice-memos/entries - don't re-answer decided stuff. -
Clarify question (at most one follow-up). If question hinges on fact not in context, ask ONE targeted question with best-modality hint. Examples:
- "Does GDPR apply?" → "Do you have analytics on your landing page, and any EU visitors? If your analytics tool is connected, I can check in 30 seconds."
- "Do I need DPA with {vendor}?" → "What data {vendor} touch - customer PII, payment data, employee data, or own company docs?" Don't ask more than one. Broad question → scope it ("narrow to {subquestion}").
-
Research if needed. For questions citing regulations, checklists, market standards, use
composio search web-search(or similar - discover at runtime) to pull authoritative sources: primary statute/regulation text, EDPB / IRS / SEC / USPTO guidance, reputable founder-legal checklists (Capbase, Andrew Bosin, Promise Legal, YC, Common Paper). Cite every source inline. No "probably" hedges - state or mark UNKNOWN. -
Draft memo (~200-400 words, direct, verb-led). Structure:
- Question - founder's question in one sentence, verbatim if possible.
- Short answer - one paragraph. First sentence = bottom line ("Yes", "No", "It depends - here's rule"). No hedging. If depends, state two or three forks + what decides between.
- Context - one paragraph: why applies to this founder. Reference entity (Delaware C-corp), stage (week 0, pre-revenue / one customer), stack (Stripe, Google Workspace), any relevant standing agreement or data geography.
- Sources cited - bulleted. Each with one-line why-it-matters. Primary statute > regulator guidance > reputable checklist. 2-5 sources, no Wikipedia.
- Next move - one concrete action in plain language. Examples: "Draft a DPA with this vendor.", "Add this vendor to your privacy vendor list.", "File 83(b) within {N} days - I can track the deadline."
- Judgment-call disclaimer - "This is a judgment call, not final legal advice. Escalate to outside counsel if {specific condition - e.g. data is health-related, customer is a regulated entity, deal over $100K}."
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.
- 12d ago First seen · 76 lines · 66 tokens per session scan A 0519703bebce
answer-a-legal-question is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 1,289 once invoked, about $0.0003 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
cve-advisory
Write CVE-format security advisories following MITRE CNA operational rules and CVE Record schema. Use when publishing vulnerability disclosures, preparing coordinated disclosure documentation, or creating vendor security advisories that require CVE identifiers.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…