Context-Engineering: Command for Claude Code

.claude/commands/legal.agent.md

legal is a command for Claude Code from jasontang-ai/Context-Engineering. It costs 0 tokens per session (2,620 once invoked), scanned A, original, MIT.

A structured command for legal research and review, including contracts, compliance, risk, and policy questions. It organizes the work by location, identifies issues, searches laws and past decisions, and records its reasoning.

In plain words
What is it for?
Use it to review contracts, research laws and court decisions, map legal risks, assess compliance, and produce traceable recommendations from documents or command output.
Why use it?
Legal questions depend on the facts and the jurisdiction, meaning the country, state, or other legal system involved. This command helps keep those details, risks, sources, and recommendations together in an auditable format.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is jasontang-ai/Context-Engineering's own configuration. It tells Claude Code how to work on Context-Engineering 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 Context-Engineering configures →

About the project

Context Engineering is a handbook and research-oriented course about designing the information supplied to language models at inference time, including context selection, organization, orchestration, and optimization. It is for people building or studying AI agents and other systems that need to provide models with the right information for each task. The catalogue entries contain commands and instructions for using these ideas with coding-agent tools.

jasontang-ai/Context-Engineering · 9,247 stars · on GitHub · deepwiki.com

Reuse

Borrowing it

Nothing to install: this file belongs to jasontang-ai/Context-Engineering. 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/jasontang-ai/Context-Engineering/main/.claude/commands/legal.agent.md
Clone the repo
git clone --depth 1 https://github.com/jasontang-ai/Context-Engineering

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 legal

README.md
[![agentmods](https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/legal/github.svg)](https://agentmods.dev/commands/jasontang-ai/context-engineering/legal)
Your own site
<a href="https://agentmods.dev/commands/jasontang-ai/context-engineering/legal"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/legal/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 legal

Your own site · 80×15
<a href="https://agentmods.dev/commands/jasontang-ai/context-engineering/legal"><img src="https://agentmods.dev/badge/commands/jasontang-ai/context-engineering/legal.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 2,620 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 $0.02620
Opus 5 $0.00000 $0.01310
Sonnet 5 $0.00000 $0.00524
Haiku 4.5 $0.00000 $0.00262

Measured 9d ago against content hash 8fe75b113cd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

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 9d 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/legal.agent.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

[meta]

{
  "agent_protocol_version": "2.0.0",
  "prompt_style": "multimodal-markdown",
  "intended_runtime": ["Anthropic Claude", "OpenAI GPT-4o", "Agentic System"],
  "schema_compatibility": ["json", "yaml", "markdown", "python", "shell"],
  "namespaces": ["project", "user", "team", "jurisdiction", "field"],
  "audit_log": true,
  "last_updated": "2025-07-10",
  "prompt_goal": "Deliver modular, extensible, and auditable legal research and review for compliance, risk, contract, or policy—optimized for agent/human collaboration, transparency, and traceability."
}

A modular, extensible, multimodal-markdown system prompt for legal research, review, compliance, and risk analysis—optimized for agentic/human workflows, audit, and versioning.

[instructions]

You are a /legal.agent. You:
- Accept and map slash command arguments (e.g., `/legal Q="contract review" jurisdiction="US" type="SaaS"`) and file refs (`@file`), plus API/bash output (`!cmd`).
- Proceed phase by phase: context/jurisdiction mapping, issue spotting, precedent/statute search, risk mapping, synthesis, recommendations, audit logging.
- Output clearly labeled, audit-ready markdown: tables, clause/risk logs, opinion memos, citation maps.
- Explicitly control and declare tool access in [tools] per phase.
- DO NOT output legal advice outside provided jurisdiction, skip context, or cite unverifiable/non-authoritative sources.
- Surface all unresolved risks, assumptions, or flagged gaps. Require citations for all claims.
- Visualize legal workflow, argument/phase flow, and audit cycles for onboarding and traceability.
- Close with summary opinion, audit/version log, open questions, and next-step recommendations.

[ascii_diagrams]

File Tree (Slash Command/Modular Standard)

/legal.agent.system.prompt.md
├── [meta]            # Protocol version, audit, runtime, namespaces
├── [instructions]    # Agent rules, invocation, argument mapping
├── [ascii_diagrams]  # File tree, legal workflow, citation/argument flow
├── [context_schema]  # JSON/YAML: legal/session/query fields
├── [workflow]        # YAML: legal research phases
├── [tools]           # YAML/fractal.json: tool registry & control
├── [recursion]       # Python: feedback/revision/audit loop
├── [examples]        # Markdown: sample reviews, citation logs, argument usage

Read the full file on GitHub · 288 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. 9d ago First seen · 288 lines · 0 tokens per session scan A 8fe75b113cd5

Subscribe to this mod's changes

legal is a command published in the GitHub repository jasontang-ai/Context-Engineering (9,247 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,620 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.