agentmods.dev

contract-review: Command for Claude Code

.claude/commands/rereview.md

rereview is a command for Claude Code from lowtidebuild/contract-review. It costs 0 tokens per session (735 once invoked), scanned A, original, Apache-2.0.

A command that starts a contract re-review workflow after a revised document is submitted. It locates the revised document and earlier review materials, then sends the work to a dedicated review agent.

In plain words
What is it for?
Finding a revised contract, identifying its prior matter and review round, loading the required reference files, and dispatching the contract review agent with a session identifier.
Why use it?
It keeps the re-review process tied to the correct earlier round and shared baselines instead of repeating the procedure informally.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is lowtidebuild/contract-review's own configuration. It tells Claude Code how to work on contract-review itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything contract-review configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is LOADER_SOURCE=root-dispatch bash .claude/scripts/load-domain-references.sh review --mode=digest --session-id="$SESSION_ID".

not rated 41repo 3mo ago A scan 0 tokens original Apache-2.0
View source ↗ lowtidebuild/contract-review
Reuse

Borrowing it

Nothing to install: this file belongs to lowtidebuild/contract-review. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lowtidebuild/contract-review/main/.claude/commands/rereview.md
Clone the repo
git clone --depth 1 https://github.com/lowtidebuild/contract-review

Made for: Claude Code.

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 rereview

README.md
[![agentmods](https://agentmods.dev/badge/commands/lowtidebuild/contract-review/rereview/github.svg)](https://agentmods.dev/commands/lowtidebuild/contract-review/rereview)
Your own site
<a href="https://agentmods.dev/commands/lowtidebuild/contract-review/rereview"><img src="https://agentmods.dev/badge/commands/lowtidebuild/contract-review/rereview/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 rereview

Your own site · 80×15
<a href="https://agentmods.dev/commands/lowtidebuild/contract-review/rereview"><img src="https://agentmods.dev/badge/commands/lowtidebuild/contract-review/rereview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 735 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 $0.00000 $0.00735
Opus 5.5 $0.00000 $0.00294
Sonnet 5.5 $0.00000 $0.00147
Haiku 4.5 $0.00000 $0.00073

Measured 1mo ago against content hash 43369036d2cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rereview 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 1mo 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.

.claude/commands/rereview.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contract Re-review — Dispatch Protocol

This command routes to Workflow 4 (Contract Re-review Pipeline). The single authoritative SOP is .claude/agents/review-agent/AGENT.md — do NOT perform the delta analysis inline in this session. Your job here is: locate the revised document and its prior round, load baselines, and dispatch the review-agent with an explicit session id.

$ARGUMENTS

Procedure (root agent)

  1. Workspace paths: Source .claude/scripts/workspace-paths.sh. Scan $CRA_INPUT_DIR first, then any distinct legacy path in $CRA_INPUT_DIRS, for the revised contract. If multiple candidate files exist, ask the user which one to re-review. If none exist, tell the user where to drop the file and stop.

  2. Resolve the prior round: An existing matter with at least one completed round must exist under $CRA_MATTERS_DIR (or the legacy contract-review/matters/ path). If the user did not supply a matter id, list the available matters with their latest round number and ask which one this revision belongs to. Do not guess.

  3. Session id (v2.2 dispatch protocol — see CLAUDE.md "Baseline Reference Load"):

    SESSION_ID="review-$(date -u +%Y%m%dT%H%M%SZ)-$$"
echo "CONTRACT_REVIEW_SESSION_ID=$SESSION_ID"

  4. Baseline digest load (root-dispatch layer of defense-in-depth):

    LOADER_SOURCE=root-dispatch bash .claude/scripts/load-domain-references.sh review --mode=digest --session-id="$SESSION_ID"

  5. Dispatch the review-agent (.claude/agents/review-agent/AGENT.md) with:

    • the revised file path,
    • matter_id and the resolved prior_round number,
    • CONTRACT_REVIEW_SESSION_ID=<session_id> verbatim,
    • any user-provided matter context (party role, review mode override, output selection, report language) passed through unresolved — the agent's Pre-Pipeline intake is the single place these get confirmed.

  6. Do not re-implement any pipeline step (round registration, parsing, clause diff, re-analysis, delta report compilation, DOCX application) in this session. All gates — JSON schema validation, validate-audience-firewall.py batch validation, strip-internal-comments.py + external-clean scan — run inside the review-agent pipeline and must not be bypassed. In particular, honor the selected deliverables: never auto-generate the external-clean DOCX unless output 2 was requested.

Read the full file on GitHub · 71 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. 1mo ago First seen · 71 lines · 0 tokens per session scan A 43369036d2cd

Subscribe to this mod's changes

rereview is a command published in the GitHub repository lowtidebuild/contract-review (41 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 735 tokens. 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

Other commands, from other repositories

/accreditation-track

Seguimiento de acreditaciones sanitarias (JCI, EFQM, ISO 9001, ISO 15189). Mapea requisitos a evidencias, detecta gaps, genera reportes de cumplimiento. Prepara auditorías y evaluaciones de terceros.

gonzalezpazmonica/pm-workspace · 56 tokens

sign

Sign a PDF — stamp a signature block (name + date, or a PNG signature) on a signed copy.

eigenweltlabs/legalwork · 22 tokens

pipeline-minutar-pdf

Pipeline completo de sentença judicial a partir de PDF (conversão, linha-tempo, relatório, análise, fundamentação, merge).

georgemarmelstein/superjurista-dev · 27 tokens

noirdoc-redact

Redact a local file via noirdoc, placing the clean copy in .noirdoc/cache/.

noirdoc-ai/mask-claude-plugin · 21 tokens

legal-risk

Analyze sourced covenant clauses and merger-agreement MAC/MAE language with page-level quotes and risk classification.

ololand-ai/ololand-plugins · 21 tokens

lawsuit-analysis

A command that analyses legal case documents and produces a structured, self-contained HTML report. It can organise people, claims, responses, evidence, and events from documents such as complaints or briefs.

llamadrive/bengo-toolkit · 24 tokens