draft-a-legal-document

draft-a-legal-document is a skill for Claude Code, Codex from akiotanaka847/qaio-desktop. It costs 84 tokens per session (2,280 once invoked), scanned A, original, MIT.

A first-draft legal document writer for common company needs, including contracts, privacy policies, board decisions, and responses to data requests. It uses your templates when available or clearly marked standard wording, and only creates drafts.

In plain words
What is it for?
Use it to draft NDAs, contractor agreements, offer letters, master services agreements, order forms, Terms of Service, Privacy Policies, board consents, and first responses to GDPR or California data requests.
Why use it?
It removes the need to start each document from a blank page while keeping the result for review by you or a lawyer. It does not send, file, or sign anything.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to draft NDAs, contractor agreements, offer letters, master services agreements, order forms, Terms of Service, Privacy Policies, board consents, and first responses to GDPR or California data requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akiotanaka847/qaio-desktop/draft-a-legal-document
Install

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.

Any agent
npx skills add akiotanaka847/qaio-desktop --skill draft-a-legal-document
Clone the repo
git clone --depth 1 https://github.com/akiotanaka847/qaio-desktop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for draft-a-legal-document

README.md
[![agentmods](https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/draft-a-legal-document/github.svg)](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/draft-a-legal-document)
Your own site
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/draft-a-legal-document"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/draft-a-legal-document/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.

agentmods 80×15 button for draft-a-legal-document

Your own site · 80×15
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/draft-a-legal-document"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/draft-a-legal-document.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,280 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.02280
Opus 5 $0.00042 $0.01140
Sonnet 5 $0.00017 $0.00456
Haiku 4.5 $0.00008 $0.00228

Measured 11d ago against content hash d29bae5b417d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

draft-a-legal-document 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 11d 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.

store/agents/legal/.agents/skills/draft-a-legal-document/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

One skill for every first-draft founder need. type param picks template + structure + citations. "Drafts only, never send / file / sign" discipline shared.

Parameter: type

Commercial paper (reads template library first):

  • nda - bilateral or one-way NDA anchored on your template.
  • consulting - consulting / contractor agreement anchored on CIIAA + deliverables + term.
  • offer-letter - employee offer letter anchored on 409A + compensation + vesting + at-will language.
  • msa - customer-facing master services agreement.
  • order-form - order form tied to existing MSA.
  • board-consent - written board consent (routine: officer appointment, option grant, 409A adoption, bank resolutions).

Privacy / policy:

  • privacy-policy - full Privacy Policy with AI-training disclosure, SCCs, subprocessor list, legal-basis citations.
  • tos - Terms of Service (usage, IP, acceptable use, liability cap, dispute forum).

Regulatory response:

  • dsr-response - GDPR Art. 15 / CCPA DSR first-touch packet: acknowledgment + identity-verification request + export cover note (3 files).

Escalation:

  • escalation-brief - structured brief for outside counsel: 2-3 sentence matter summary, specific questions for lawyer, quoted excerpts with cite, deadline, recommended firm type (corporate / commercial lit / privacy / IP / employment). Never names specific firms.

User names type in plain English ("draft NDA with Acme", "write our privacy policy", "package this for counsel") → infer. Ambiguous → ask ONE question naming 10 options grouped by bucket.

When to use

  • Explicit: "draft {type}", "write our privacy policy", "respond to this DSR", "escalate this to counsel".
  • Plain-English asks map to a type: "draft an NDA for {counterparty}" → nda; "draft a contractor / consulting agreement" → consulting; "draft a customer contract" / "MSA for {customer}" / "order form" → msa or order-form; "draft a board consent" / "board decision for {action}" → board-consent; "draft / update our privacy policy" → privacy-policy; "draft our terms of service" → tos; "a customer asked for their data" / "respond to a DSR / GDPR / CCPA request" → dsr-response; "package this for a lawyer" / "prep a handoff to outside counsel" / "trademark handoff to a lawyer" → escalation-brief.
  • Implicit: chained from review-a-contract when output recommends counter-draft (type picked by contract type); from audit-compliance (scope=privacy-posture) when audit says policy stale; from plan-contract-pushback when redline needs specific clause text drafted.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 11d ago First seen · 95 lines · 84 tokens per session scan A d29bae5b417d

Subscribe to this mod's changes

draft-a-legal-document is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 7d ago), licensed MIT. It adds 84 tokens to every session and 2,280 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 2026-08-31.

Related

Other skills, from other repositories

uk-particulars-of-claim-review

Use when users say "review these Particulars of Claim", "check this PoC", "pleading gaps", "CPR 16", "PD16", "limitation issue", or need England and Wales pleadings checked for elements, material facts, remedies, parties, source support, and drafting risk.

LegalQuants/lq-skills · 72 tokens

uk-witness-statement-review

Use when users say "review this witness statement", "check this statement before service", "PD 57AC", "statement of truth", "hearsay in this witness evidence", or need England and Wales witness evidence checked for source support, CPR/PD issues, exhibits, chronology conflicts, or argument.

LegalQuants/lq-skills · 69 tokens

Brief Section Drafter

Use when drafting a single section of a litigation brief — such as a statement of facts, argument section, standard of review, or conclusion — that is cited to the record, consistent with the case theory, and fully flagged for attorney verification before filing.

zgbrenner/agentcounsel · 55 tokens

Board Minutes

Use when drafting minutes of a board of directors or board-committee meeting as a corporate record, producing a structured draft for attorney review.

zgbrenner/agentcounsel · 30 tokens

Shareholder Meeting Minutes

Use when drafting minutes of a shareholder or member meeting (annual or special) from user-provided meeting materials — notice, agenda, proxy materials, attendance, and vote tallies — producing a structured draft corporate record for attorney review.

zgbrenner/agentcounsel · 51 tokens

Written Consent

Use when drafting a board or board-committee action by written consent in lieu of a meeting to produce a structured draft for attorney review.

zgbrenner/agentcounsel · 30 tokens