agentmods.dev

deeplaw-promote-draft

deeplaw-promote-draft is a skill for Claude Code, Codex from Eysn0130/DeepLaw. It costs 47 tokens per session (232 once invoked), scanned A, original, Apache-2.0.

A narrowly controlled skill for reviewing and promoting a specific DeepLaw Knowledge draft. DeepLaw is a governed system for storing and managing legal knowledge, and promotion means accepting a draft into that system.

In plain words
What is it for?
Verifying a named draft, checking its sources and scope, detecting duplicates, and proposing or carrying out promotion only when the required owner permission is present.
Why use it?
It prevents an agent from automatically turning unverified or sensitive material into approved knowledge. The process requires an exact draft, owner direction, source checks, and recorded review details.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the deeplaw-knowledge-os plugin — 8 skills, 5 hooks shipped together

not rated 6repo 1mo ago A scan 47 tokens original Apache-2.0

Good fit Verifying a named draft, checking its sources and scope, detecting duplicates, and proposing or carrying out promotion only when the required owner permission is present.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eysn0130/deeplaw/deeplaw-promote-draft
View source ↗ Eysn0130/DeepLaw
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 Eysn0130/DeepLaw --skill deeplaw-promote-draft
Clone the repo
git clone --depth 1 https://github.com/Eysn0130/DeepLaw

Made for: Claude Code, Codex.

Or install deeplaw-knowledge-os, the plugin that ships this one along with the rest of its 8 skills, 5 hooks.

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 deeplaw-promote-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/eysn0130/deeplaw/deeplaw-promote-draft/github.svg)](https://agentmods.dev/skills/eysn0130/deeplaw/deeplaw-promote-draft)
Your own site
<a href="https://agentmods.dev/skills/eysn0130/deeplaw/deeplaw-promote-draft"><img src="https://agentmods.dev/badge/skills/eysn0130/deeplaw/deeplaw-promote-draft/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 deeplaw-promote-draft

Your own site · 80×15
<a href="https://agentmods.dev/skills/eysn0130/deeplaw/deeplaw-promote-draft"><img src="https://agentmods.dev/badge/skills/eysn0130/deeplaw/deeplaw-promote-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 232 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 $0.00047 $0.00232
Opus 5.5 $0.00019 $0.00093
Sonnet 5.5 $0.00009 $0.00046
Haiku 4.5 $0.00005 $0.00023

Measured 2mo ago against content hash 07567df7237e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

deeplaw-promote-draft 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.

plugins/deeplaw-knowledge-os/skills/deeplaw-promote-draft/SKILL.md · 19 lines

What it actually says

Promote an Admitted Draft

Require an exact draft_id, explicit owner direction, and confirm_no_case_data=true.

  1. Read and verify the draft, its source references, scope, sensitivity, provenance, and duplicate checks with knowledge_support before proposing any action.
  2. Require a separately owner-created Grant for knowledge_sink allowing only promote_knowledge_draft, or require an explicit owner CLI action. Never create, widen, inspect, or copy a Grant.
  3. Require the recorded evaluator, reason, and any external or owner check. Preserve origin=agent_derived, legal_authority=false, scope, sensitivity, and immutable lineage.
  4. Never promote automatically, invoke a model automatically, mutate Markdown directly, or turn ranking into Authority. Report rejection, quarantine, or successful promotion exactly.
Files

What ships with it

1 file 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. 2mo ago First seen · 19 lines · 47 tokens per session scan A 07567df7237e

Subscribe to this mod's changes

deeplaw-promote-draft is a skill published in the GitHub repository Eysn0130/DeepLaw (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 232 once invoked, about $0.0002 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 2026-08-31.

Claude CodeLegal and compliancechinese-lawcodexlegal-researchmcpopencode
Related

deeplaw-promote-draft compared with skills from other repositories

deeplaw-promote-draft next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
deeplaw-promote-draftEysn0130/DeepLawSkill61mo agoApache-2.0A47Claude Code, Codex
contract-guardianlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA245Claude Code, Codex
法律周报lawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA242Claude Code, Codex
legal-researchlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA87Claude Code, Codex
legal-citation-comprehensivelawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA119Claude Code, Codex
legal-fact-checkerlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA143Claude Code, Codex
workflow-overviewlawyerllsx-dotcom/Legal-Workflow-ChainSkill51mo agoMITA63Claude Code, Codex