agentmods.dev

qa

qa is a skill for Claude Code, Codex from anylegal-ai/anylegal-oss. It costs 31 tokens per session (1,002 once invoked), scanned A, original, MIT.

A quality-checking process for legal documents and related work. It reviews whether a document follows its required template, contains accurate facts, is complete, reflects changes, records research properly, and follows instructions.

In plain words
What is it for?
Use it when a legal matter moves from working to review, after document edits, or when counsel requests another check. It checks contracts and supporting files against templates, instructions, playbooks, research, and the original document.
Why use it?
It helps find missing clauses, incorrect numbering, broken references, leftover placeholders, factual errors, and other problems before a document is sent for review or use.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 17repo +2 24d ago A scan 31 tokens original MIT

Good fit Use it when a legal matter moves from working to review, after document edits, or when counsel requests another check. It checks contracts and supporting files against templates, instructions, playbooks, research, and the original document.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anylegal-ai/anylegal-oss/qa
View source ↗ anylegal-ai/anylegal-oss
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 anylegal-ai/anylegal-oss --skill qa
Clone the repo
git clone --depth 1 https://github.com/anylegal-ai/anylegal-oss

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 qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/anylegal-ai/anylegal-oss/qa/github.svg)](https://agentmods.dev/skills/anylegal-ai/anylegal-oss/qa)
Your own site
<a href="https://agentmods.dev/skills/anylegal-ai/anylegal-oss/qa"><img src="https://agentmods.dev/badge/skills/anylegal-ai/anylegal-oss/qa/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 qa

Your own site · 80×15
<a href="https://agentmods.dev/skills/anylegal-ai/anylegal-oss/qa"><img src="https://agentmods.dev/badge/skills/anylegal-ai/anylegal-oss/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,002 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 $0.00031 $0.01002
Opus 5.5 $0.00012 $0.00401
Sonnet 5.5 $0.00006 $0.00200
Haiku 4.5 $0.00003 $0.00100

Measured 2mo ago against content hash 25f10dfe8030, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa 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 2mo 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.

backend/anylegal_oss/workspace/skills/qa/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Assurance Review

When to Use

Use this skill when:

  • The user says /qa
  • A matter is transitioning from WORKING to REVIEW
  • Counsel requests a fresh QA pass after a return
  • The agent has finished editing a document and needs verification

Process

1. Inventory the Workspace

Call list_documents to see all files. Identify:

  • The primary deliverable (the main contract/document being worked on)
  • The intake summary (intake_*.md) for client instructions
  • Any playbook files (Playbook/*.md, anylegal.md)
  • Any research notes or memos created during the work
  • The original uploaded document (if different from the deliverable)

2. Template Compliance Check

Read the deliverable with read_document. Check:

  • Document structure matches the expected template format
  • Clause numbering is sequential and correct
  • Cross-references (to other clauses, schedules, annexes) are accurate
  • Defined terms are used consistently (capitalization, spelling)
  • No placeholder text remains (e.g., "[INSERT]", "TBD", "XXX")
  • Standard boilerplate clauses are present (severability, governing law, etc.)

3. Factual Accuracy Check

Verify legal facts in the document:

  • Jurisdiction references are correct for the matter type
  • Legal citations (statutes, regulations, case law) are valid — use web_search to spot-check
  • Dates, deadlines, and time periods are internally consistent
  • Party names and entity types are correct throughout
  • Currency and monetary amounts are consistent

4. Completeness Check

Read the intake summary and compare against the deliverable:

  • All client instructions from intake have been addressed
  • All documents mentioned in intake have been reviewed/incorporated
  • No sections are left unfinished or contain TODO markers
  • If multi-jurisdictional, all specified jurisdictions are covered

5. Track Changes Review

Use run_code (default Python) with lxml to count tracked changes (w:ins, w:del), extract authors, and assess edit scope. Then:

  • Every insertion has a clear purpose (improves protection, fixes error, adds required clause)
  • Every deletion is justified (removes risk, corrects error, simplifies)
  • No unintended formatting-only changes
  • Tracked changes are clean (no stacked/overlapping revisions)
  • Total edit count is proportionate to the matter scope

Read the full file on GitHub · 128 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. 2mo ago First seen · 128 lines · 31 tokens per session scan A 25f10dfe8030

Subscribe to this mod's changes

qa is a skill published in the GitHub repository anylegal-ai/anylegal-oss (17 stars, last pushed 24d ago), licensed MIT. It adds 31 tokens to every session and 1,002 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

DocumentsLegal and compliance
Related

qa compared with skills from other repositories

qa next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
qaanylegal-ai/anylegal-ossSkill1724d agoMITA31Claude Code, Codex
html-ppt-zhangzara-stencil-tabletnexu-io/open-designSkill106kyesterdayApache-2.0A49Claude Code, Codex
treatment-plansK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA62Claude Code, Codex
legal-holdanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A68Claude Code
handbook-updatesanthropics/claude-for-legalSkill9.9k3d agoApache-2.0A52Claude Code
terms-of-servicegenspark-ai/genofficeSkill12kyesterdayApache-2.0A32Claude Code, Codex
software-copyright-materialsFokkyp/SoftwareCopyright-SkillSkill6.3k14d agoAGPL-3.0A98Claude Code, Codex