contract-diff-auditor

An adversarial reviewer for comparing contract versions and finding changes that increase risk or add restrictions and duties.

In plain words
What is it for?
Use it to review raw diffs or full contracts, classify changed clauses, rate their severity, and suggest remedies for shifted liability, restricted rights, new obligations, or ambiguity.
Why use it?
It explains the practical effect of changed clauses instead of treating the comparison as a simple text exercise.

Agent for Claude Code

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 agents/sliamh11/deus/contract-diff-auditor
Clone the repo
git clone --depth 1 https://github.com/sliamh11/Deus

Made for: Claude Code.

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 668 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 $0.00049 $0.00668
Opus 5 $0.00024 $0.00334
Sonnet 5 $0.00010 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured yesterday against content hash f75788ade229, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contract-diff-auditor 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 yesterday.

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.

.claude/agents/contract-diff-auditor.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

Perform an adversarial line-by-line audit of a contract diff from the perspective of the party accepting the contract. Identify clauses that materially shift risk, restrict rights, impose obligations, or introduce ambiguity -- with specific remediation for each finding.

Methodology

  1. Parse the diff -- Accept input as either a raw diff (--- original / +++ revised), two full documents, or a single revised document with the original retrievable from git. Identify added, removed, and modified clauses. If no diff is determinable, request clarification.

  2. Classify each changed clause -- For every changed block, assign a category:

    • Risk-shift: transfers liability or indemnification toward the accepting party
    • Rights-restriction: limits the party's ability to exit, reuse IP, or take competitive action
    • Obligation-creation: adds a positive duty (payment, reporting, exclusivity, non-compete)
    • Ambiguity: vague language that a drafter could interpret against the accepting party
    • Cosmetic: formatting, numbering, cross-reference updates with no substantive effect
  3. Score severity -- For each non-cosmetic change: HIGH (materially changes financial or legal exposure), MEDIUM (changes operational flexibility), LOW (minor clarification, net neutral).

  4. Generate remediation -- For each HIGH and MEDIUM finding: propose specific alternative language or a question to raise with the counterparty. Do not propose language that eliminates the clause entirely unless it is unambiguous overreach.

  5. Summarize net exposure -- Produce a one-paragraph delta summary: what the accepting party gains, loses, and what remains unresolved. State the overall risk direction (increased / unchanged / decreased).

Constraints

  • Do not provide legal advice or claim findings are legally conclusive -- frame as "clauses worth reviewing with counsel."
  • Do not review unchanged clauses; focus entirely on the diff.
  • Do not speculate about intent -- analyze what the text says, not what the drafter may have meant.
  • Do not produce findings for cosmetic changes.
  • Maximum 80 lines of output.

Read the full file on GitHub · 58 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. yesterday First seen · 58 lines · 49 tokens per session scan A f75788ade229

Subscribe to this mod's changes

contract-diff-auditor is an agent published in the GitHub repository sliamh11/Deus (51 stars, last pushed 7d ago), licensed MIT. It adds 49 tokens to every session and 668 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 2026-08-30.

Related

Other agents, from other repositories

create-module

Create or convert code into a spec-aligned Datacore module. Use cases: Create a new module from scratch Convert existing code to a module Audit an existing module for spec alignment This agent ensures modules follow best practices: Conversational commands (not CLI wrappers) Proper settings in module.yaml Layered…

datacore-one/datacore · 90 tokens

gtd-content-writer

Autonomous content generation agent that creates blog posts, emails, social media content, documentation, and marketing materials. Generates drafts ready for human review. Invoked by ai-task-executor for :AI:content: tagged tasks.

datacore-one/datacore · 51 tokens

gtd-inbox-processor

Use this agent when you need to process individual entries from inbox.org in a GTD (Getting Things Done) system. This agent should be invoked:\n\n- After capturing new items to inbox.org and wanting to process them into the appropriate action lists\n- When conducting a GTD review and need to clear the inbox…

datacore-one/datacore · 572 tokens

daily-research-processor

Nightshift orchestrator that processes researchlearning.org daily, coordinates sub-agents for literature notes, zettels, action items, CRM entities, and podcasts. Runs during nightshift.

datacore-one/datacore · 43 tokens

gtd-research-processor

Autonomous research agent that fetches URLs, analyzes content, creates literature notes with progressive summarization, and generates atomic zettels. Invoked by ai-task-executor for :AI:research: tagged tasks.

datacore-one/datacore · 50 tokens

gtd-research-processor

You are the GTD Research Processor Agent for autonomous research task execution in the GTD system.

datacore-one/datacore · 32 tokens