legalant: Instructions file for Claude Code

CLAUDE.md

legalant CLAUDE.md is an instructions file for Claude Code from ishwarjha/legalant. It costs 2,870 tokens per session, scanned C, original, MIT.

Repository guidance for Claude Code work on LegalAnt, a plugin made mainly from Markdown agent specifications and a few installer and Node.js server files.

In plain words
What is it for?
Use it to understand the plugin layout, its common commands, its architecture, and how its installers and server components fit together.
Why use it?
It explains the repository structure and limits, so changes are made in the right places without assuming it is a normal application with a build or test suite.

Instructions file for Claude Code

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

This is ishwarjha/legalant's own configuration. It tells Claude Code how to work on legalant 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 legalant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ishwarjha/legalant. 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/ishwarjha/legalant/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ishwarjha/legalant

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 legalant CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ishwarjha/legalant/claude-md/github.svg)](https://agentmods.dev/instructions/ishwarjha/legalant/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ishwarjha/legalant/claude-md"><img src="https://agentmods.dev/badge/instructions/ishwarjha/legalant/claude-md/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 legalant CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ishwarjha/legalant/claude-md"><img src="https://agentmods.dev/badge/instructions/ishwarjha/legalant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,870 This file is loaded in full into every session.
When invoked 2,870 The same file — it is already loaded in full.
Security scan C 2 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 $0.02870 $0.02870
Opus 5 $0.01435 $0.01435
Sonnet 5 $0.00574 $0.00574
Haiku 4.5 $0.00287 $0.00287

Measured 10d ago against content hash 0f6e444cb115, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

legalant CLAUDE.md scanned grade C with 2 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 10d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/ishwarjha/legalant/main/install-legalant.sh | bash -s -- all

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/ishwarjha/legalant/main/install-legalant.sh | bash -s -- all
CLAUDE.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Repository Is

LegalAnt is a Claude Code plugin, not a runtime application. There is no build, no test runner, and no server. Every "agent" is a Markdown spec file with YAML frontmatter — no Python or JS in the agent layer. The only executable code is:

  • install.sh / install-legalant.sh — bash installers that copy plugin assets into ~/.claude/ or a target project's .claude/
  • mcp-servers/{pdf-ocr-processor,rbi-scraper,sebi-scraper}/index.js — Node MCP servers (each has its own package.json)
  • Per-matter package.json scripts that agents generate at runtime to render DOCX (created and deleted as throwaway code, not committed)

Repository Layout (the part that matters)

legalant/                          ← repo root
  legalant/                        ← THE PLUGIN (this is what gets distributed)
    .claude-plugin/plugin.json
    agents/    ← 18 agent spec .md files (lexis + 4 layer-1 + 4 orchestrators + 5 practice + 4 utility)
    commands/  ← 16 slash commands that invoke those agents
    skills/{contract-basics,word-choice,universal-standards,indian-law-defaults}/SKILL.md
  .claude-plugin/marketplace.json  ← marketplace manifest (separate from the plugin's own manifest)
  .claude/agents/                  ← duplicates of legalant/agents/ — installed copy for local dev
    mcp-servers/{pdf-ocr-processor,rbi-scraper,sebi-scraper}/  ← Node MCP servers, declared in plugin.json
  rules/                           ← extra .md skills that the plugin can't auto-distribute (installed via install.sh)
  schemas/                         ← JSON shapes for matter.json, hitl-log.json, dd-register.json, etc.
  scripts/office/validate.py       ← post-render DOCX validator (every agent calls this)
  matters/                         ← .gitignored runtime workspace; one folder per LA-YYYY-NNN matter

The duplicated content in legalant/agents/ and .claude/agents/ is intentional: legalant/agents/ is the plugin source-of-truth that ships to users; .claude/agents/ is the locally-installed copy. Edits must be made to legalant/agents/ and propagated (the installer copies one to the other; do not assume one is canonical without checking the diff).

Read the full file on GitHub · 157 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. 10d ago First seen · 157 lines · 2,870 tokens per session scan C 0f6e444cb115

Subscribe to this mod's changes

legalant CLAUDE.md is an instructions file published in the GitHub repository ishwarjha/legalant (6 stars, last pushed 4mo ago), licensed MIT. It adds 2,870 tokens to every session, about $0.0144 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens