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 sort-my-legal-inboxgit 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/sort-my-legal-inbox)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/sort-my-legal-inbox"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/sort-my-legal-inbox/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/sort-my-legal-inbox"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/sort-my-legal-inbox.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 | $0.00053 | $0.01152 |
| Opus 5 | $0.00026 | $0.00576 |
| Sonnet 5 | $0.00011 | $0.00230 |
| Haiku 4.5 | $0.00005 | $0.00115 |
Grade A, and why
sort-my-legal-inbox 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sort My Legal Inbox
When to use
- Explicit: "triage my legal inbox", "sweep inbound for contracts", "what legal email needs me", "run intake".
- Implicit: first skill the user runs when they see a "Needs you" card and ask "what's waiting on me?"
- Safe on-demand - daily or few times/week for solo founder. Default window: last 7 days if unspecified.
Steps
- Read shared context:
context/legal-context.md. If missing/empty, ask the user in plain language: "I need a few basics about your company first. Want to set those up now?" Then runset-up-my-legal-infoif yes. Stop until that's done. - Read config:
config/counterparty-stack.json. If your inbox isn't connected, ask the user in plain language: "I need to connect your inbox to look through it. Want to connect Gmail or Outlook now?" Stop until connected. - Discover inbox tool via Composio. Run
composio search inboxfor tool slug. Confirm slug matchescounterparty-stack.inboxCategory. - Pull inbound. Default window: last 7 days (or user N). Query inbox slug for likely-legal messages - contract attachments (.pdf, .docx), law-firm sender domains, subject keywords ("NDA", "MSA", "DPA", "DSR", "subpoena", "office action", "terms", "agreement"), threads replying to prior legal inbound.
- Classify each item. Apply rubric, pick one bucket:
- NDA - traffic-light: Green = mutual, ≤3-year term, reasonable scope, standard non-solicit (or none), no unusual residuals, no non-compete, US governing law. Yellow = exactly one deviation (one-way where we sole discloser, 3-5 year term, broad residuals, adjacent jurisdiction like Canada/UK). Red = two+ deviations, or any of: non-compete, IP assignment, unlimited liability, publicity / press-release obligations, term >5 years or perpetual, non-standard governing law. Default Red if text not confidently parsed.
- MSA / order form - umbrella or commercial-terms doc from customer/vendor.
- DPA - data-processing addendum or stand-alone data terms.
- DSR - data-subject request (GDPR Art. 15, CCPA).
- subpoena / legal process - subpoena, preservation demand, cease-and-desist, litigation hold.
- TM office action - USPTO office action or TM correspondence.
- contractor paper - inbound consulting / contractor / work-for-hire from counterparty.
- other - anything else legal-flavored (insurance-cert request, privacy inquiry, vendor security questionnaire).
- Route each item. Recommend one:
- self-handle via
draft-a-legal-document- only if item maps cleanly to existing template (e.g. Green NDA with known counterparty). - send to
review-a-contract(mode=full) - most MSA / DPA / order-form / Yellow NDAs go here. - flag
attorneyReviewRequired- Red NDAs, subpoenas, litigation-adjacent, anything ambiguous. - ignore - spam, newsletters, resolved threads.
- self-handle via
- Write summary to
intake-summaries/{YYYY-MM-DD}.mdatomically (*.tmp→ rename). Structure: counts at top ("7 items: 3 NDA, 1 MSA, 1 DSR, 2 other"), then one section per item withFrom,Subject,Received,Classification,One-line summary,Recommended route. - Append to
outputs.json- read existing array, add{ id, type: "intake-summary", title, summary, path, status: "draft", createdAt, updatedAt, attorneyReviewRequired }. SetattorneyReviewRequired: trueif any item flagged for attorney review. - Summarize to user. Plain language. One short paragraph: "I found {N} legal items. {X} NDAs (with the safe ones flagged), {Y} customer contracts, {Z} that need a real lawyer's eyes. Want me to draft replies for the safe ones, or fully review the customer contracts?" Never name files or paths.
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 · 51 lines · 53 tokens per session scan A a5bcd82e7e8e
sort-my-legal-inbox is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 53 tokens to every session and 1,152 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
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…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…