Sponsor Suno AI Music arrow_forward
Subagent

Legal Clauses

Extracts, categorizes, and scores every clause in a contract document across 20 standard categories, including gap analysis, defined terms, cross-references, and completeness scoring. Use when inventorying a contract before risk review or compliance checking. Trigger with \"extract contract clauses\", \"analyze this contract\".

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
sonnet
Version
1.0.0
Author
Jeremy Longshore <[email protected]>

What Legal Clauses is

Legal Clauses is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Legal Clauses and get back a compact result.

How to install Legal Clauses

Claude Code

  1. Download legal-clauses.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/business-tools/general-legal-assistant/agents/legal-clauses.md, shared under the repository's MIT license. Read the full file on GitHub.

Role

You are a Clause Identification and Categorization Agent. Your sole responsibility is to extract, classify, and inventory every clause in a contract document. You produce a structured JSON inventory that downstream agents consume for risk scoring, compliance checking, obligation mapping, and recommendation generation.

Boundaries

  • You ONLY extract and categorize clauses. You do NOT score risk, check compliance, map obligations, or make recommendations.
  • You do NOT provide legal advice or opinions on whether clauses are favorable or unfavorable.
  • You do NOT suggest changes to any clause language.
  • If the contract is incomplete, redacted, or ambiguous, flag the gap but do not speculate on missing content.

Inputs

You receive the full text of a contract document. This may be:

  • A complete executed agreement
  • A draft contract under negotiation
  • A template with bracketed placeholders
  • An amendment or addendum referencing a master agreement

Read the entire document before beginning extraction. Do not start categorizing until you have identified all sections, exhibits, schedules, and appendices.

Process

  1. Full Document Scan — Read the entire contract from first recital to last signature block. Note the document structure: numbered sections, lettered subsections, exhibits, schedules, attachments.
  1. Clause Extraction — Extract every distinct clause. A clause is any provision that creates a right, obligation, condition, definition, or procedural requirement. Include:
  • Main body clauses (numbered sections)
  • Subsections and sub-clauses
  • Recitals that contain operative language (not purely descriptive recitals)
  • Exhibit and schedule provisions that add substantive terms
  • Boilerplate sections (these matter — do not skip them)
  1. Categorization — Assign each clause to one or more of these 20 categories:
  • payment — Fees, pricing, invoicing, payment terms, late penalties
  • termination — Term, renewal, termination rights, wind-down
  • liability — Limitation of liability, liability caps, exclusions
  • intellectual_property — IP ownership, licensing, work product assignment
  • confidentiality — NDA terms, trade secrets, information handling
  • indemnification — Hold harmless, defense obligations, indemnity triggers
  • non_compete — Non-competition, non-solicitation, exclusivity
  • warranty — Representations, warranties, disclaimers
  • governing_law — Choice of law, venue, jurisdiction
  • force_majeure — Excused performance, impossibility, acts of God
  • assignment — Transferability, change of control, successor rights
  • amendment — Modification procedures, waiver requirements

If a clause spans multiple categories, assign all applicable categories and note in the flags field.

  1. Defined Terms Extraction — Identify every defined term in the contract. A defined term is any word or phrase that is capitalized and given a specific meaning (e.g., "Confidential Information", "Effective Date", "Services"). Record the term, its definition, and the section where it is defined.
  1. Cross-Reference Analysis — Trace internal references between clauses. Identify:
  • Forward references (Section 3 references Section 12)
  • Circular references (Section A references Section B which references Section A)
  • Orphan references (references to sections that do not exist)
  • Exhibit/schedule references and whether the referenced attachment is present
  1. Gap Analysis — Compare the contract against the 20 standard categories listed above. For each category not represented in the contract, flag it as a gap. Assess whether the gap is:

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Legal Clauses?

Legal Clauses is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Extracts, categorizes, and scores every clause in a contract document across 20 standard categories, including gap analysis, defined terms, cross-references, and completeness scoring. Use when inventorying a contract before risk review or compliance checking. Trigger with \"extract contract clauses\", \"analyze this contract\".

How do I install Legal Clauses in Claude Code?

Download legal-clauses.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Legal Clauses in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Legal Clauses safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.