internal/legal

internal/legal is a skill for Claude Code, Codex from quantDIY/GERP. It costs 37 tokens per session (211 once invoked), scanned A, original, MIT.

An internal legal and compliance module for tracking contracts and keeping an append-only audit record. SOX and SOC 2 are standards for financial controls and information-security controls.

In plain words
What is it for?
Use it for contract tracking, compliance work, and audit logging across business systems.
Why use it?
It provides a defined place to record compliance activity and preserve a history of changes that should not be edited or deleted.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/quantdiy/gerp/legal
Any agent
npx skills add quantDIY/GERP --skill legal
Clone the repo
git clone --depth 1 https://github.com/quantDIY/GERP

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 internal/legal

README.md
[![agentmods](https://agentmods.dev/badge/skills/quantdiy/gerp/legal.svg)](https://agentmods.dev/skills/quantdiy/gerp/legal)
Your own site
<a href="https://agentmods.dev/skills/quantdiy/gerp/legal"><img src="https://agentmods.dev/badge/skills/quantdiy/gerp/legal.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.00211
Opus 5 $0.00018 $0.00105
Sonnet 5 $0.00007 $0.00042
Haiku 4.5 $0.00004 $0.00021

Measured 5d ago against content hash 0eb31ba7b6fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

internal/legal 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.

internal/legal/SKILL.md · 19 lines

What it actually says

This module enforces immutable corporate governance. It tracks active B2B/B2C contracts and maintains a strict SOX/SOC2 compliance audit log across the entire matrix.

Constraints

  • Zero Foreign Keys: CounterpartyID tracks back to MDM. TargetRecordID tracks any UUID across all Domains. ActorID tracks to HCM.
  • Immutability: ComplianceAudits are append-only. They mathematically prove physical state changes across the system.
Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 19 lines · 37 tokens per session scan A 0eb31ba7b6fd

Subscribe to this mod's changes

internal/legal is a skill published in the GitHub repository quantDIY/GERP (3 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 211 once invoked, about $0.0002 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

sap-gts

This skill handles SAP GTS (Global Trade Services) tasks including export/import compliance, Sanctioned Party List screening, license management, customs declaration, HS code classification, Letter of Credit, preference determination, and Korea Customs Service (UNI-PASS) integration. Use when user mentions GTS, global…

BoxLogoDev/sapstack · 150 tokens

contract-audit

Search uploaded contracts and documents for clauses such as auto-renewal, notice periods, liability caps and payment terms, and cross-reference them with the client's finances. Use when asked what a contract says, which agreements renew, or to review terms across clients.

RunButter/runbutter · 55 tokens

screen-a-new-client

Run the checks that should happen before invoicing a new client — sanctions screening, company registry lookup, and IBAN validation. Use when onboarding a customer, before a first invoice, or when asked to verify a company or bank account.

RunButter/runbutter · 52 tokens

speckit-specify

Create a specification for Leopardo HR with payroll compliance gates automatically injected.

kitokoh/leopardo-hr · 20 tokens

compliance-audit

合规审计 SOP。用户说"合规"、"认证"、"召回"、"CPSC"、"CE"、"RoHS"、"REACH"、"compliance"、"audit" 时触发。检查认证缺口、召回风险、CBAM影响、系统数据一致性。.

JiuTian-dev/SupplyChainCortex · 76 tokens

specification-writing

Write the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens