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-policy-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-policy-question)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/answer-a-policy-question"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/answer-a-policy-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-policy-question"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/answer-a-policy-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 | $0.00061 | $0.01630 |
| Opus 5 | $0.00030 | $0.00815 |
| Sonnet 5 | $0.00012 | $0.00326 |
| Haiku 4.5 | $0.00006 | $0.00163 |
Grade A, and why
answer-a-policy-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 6d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer a Policy Question
When to use
- Explicit: "does {employee} qualify for {PTO / leave / parental / bereavement / remote}", "can {employee} expense {X}", "what's our policy on {topic}", "is this covered".
- Template variant: "draft the PTO (or {topic}) reply template", "give
me reusable variants for {policy} asks" - produce all three reply
paths (direct / ambiguous / escalation) for the named topic and save
to
approvals/{topic}-reply-template.mdfor reuse. - Implicit: routed from helpdesk-channel watcher (Slack listener, Gmail filter) when team member asks HR question.
- Frequency: as often as team members ask. Classifier run every time.
Connections I need
I run external work through Composio. Before this skill runs I check that the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Docs (Google Docs, Notion) — read the handbook or policy doc when it lives outside this agent. Optional.
- Inbox (Gmail) — match your reply voice. Optional.
- Chat (Slack) — reply where the question came in. Optional.
This skill never sends without your sign-off, so no integration is strictly required — but a connected handbook keeps me from asking questions you've already answered.
Information I need
I read your people context first. For every required field that's missing I ask ONE plain-language question (best modality: connected app > file drop > URL > paste) and wait.
- The question being asked — Required. Why I need it: I classify and answer the specific ask. If missing I ask: "What's the question, and who's asking?"
- Policy canon — Required. Why I need it: every direct answer cites the relevant policy. If missing I ask: "Drop your current handbook or share a link to it, or run set-up-my-people-info first to capture the policies."
- Escalation rules — Required. Why I need it: I never draft answers on discrimination, harassment, wage, or visa-law questions — I route them. If missing I ask: "Who do discrimination, harassment, wage-dispute, and visa questions route to. Is there a named lawyer, or should we mark it TBD until you have one?"
- Jurisdiction — Optional. Why I need it: leave and benefits answers vary by state and country. If you don't have it I keep going with TBD and surface jurisdictional gaps in the draft.
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.
- 6d ago First seen · 131 lines · 61 tokens per session scan A 87c0c82a2659
answer-a-policy-question is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,630 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 2026-09-05.
Other skills, from other repositories
role-credential-readiness
Flag credentials a role legally requires.
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…