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 read-a-contractgit 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/read-a-contract)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/read-a-contract"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/read-a-contract/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/read-a-contract"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/read-a-contract.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 | $0.00081 | $0.01291 |
| Opus 5 | $0.00041 | $0.00646 |
| Sonnet 5 | $0.00016 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
read-a-contract 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 5d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read A Contract
When to use
- "pull the {clause} from this contract" (single doc).
- "what are the auto-renew terms in every contract in this folder" (batch).
- "extract the liability cap and termination language from {vendor}'s master service agreement".
Connections I need
I run external work through Composio. Before this skill runs I check the categories below are linked. Missing → I name the category, ask you to connect it from the Integrations tab, stop.
- Files (Google Drive) - Required for batch runs and named-vendor lookups. I scan folders or named contracts here.
- Document processing (OCR or PDF text extraction) - Required. Pulls the actual text out of scanned or native PDFs so I can extract clauses verbatim.
If no files provider is connected and you haven't pasted the contract, I stop and ask you to connect Google Drive or paste the document.
Information I need
I read your operations 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 contract itself - Required. Why I need it: I can't extract from nothing. If missing I ask: "Drop the contract or point me at the folder. PDF, Word, or a Google Doc all work."
- Vendor posture - Required. Why I need it: tells me which terms count as a flag. A conservative posture flags more aggressively than fast-risk. If missing I ask: "How do you approach vendor terms - conservative, balanced, or move fast?"
- Operating context doc - Required. Why I need it: anchors hard nos so I flag clauses that would violate them. If missing I ask: "Want me to set up your operating context first? Helps me catch unfavorable terms more reliably."
Steps
-
Read
context/operations-context.md. If missing: stop, ask user runset-up-my-ops-infoskill first. Vendor posture + hard nos anchor "unfavorable terms" flags. -
Read
config/procurement.json- approval posture decide which terms count as "flag worthy" (conservative founder flag more; fast-risk founder flag only truly egregious).
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.
- 5d ago First seen · 83 lines · 81 tokens per session scan A abc72cc97d30
read-a-contract is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 6d ago), licensed MIT. It adds 81 tokens to every session and 1,291 once invoked, about $0.0004 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
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
software-certificate-skill
An automated workflow for preparing Chinese software-copyright registration materials from a real software project. It produces application information, an operation manual, and source-code documents with evidence from the project.