What is counsel-os CLAUDE.md?

Developer guidance for Counsel OS, a Claude Code plugin that supports legal practice through five reusable actions: reading, researching, evaluating, drafting, and remembering. It also includes legal reference files, matter-management instructions, templates, and document redlining utilities.

Researching and evaluating legal matters, drafting documents, managing matter knowledge, refreshing legal references, importing sources, and applying or comparing document redlines.

It gives the assistant a structured way to handle legal work and reuse knowledge without forcing every request through one fixed pipeline. The repository layout shows where legal references, skills, practice templates, and document tools belong.

How eigenlegal/counsel-os configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to eigenlegal/counsel-os. 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/eigenlegal/counsel-os/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/eigenlegal/counsel-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/eigenlegal/counsel-os/claude-md/github.svg)](https://agentmods.dev/instructions/eigenlegal/counsel-os/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/eigenlegal/counsel-os/claude-md"><img src="https://agentmods.dev/badge/instructions/eigenlegal/counsel-os/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/eigenlegal/counsel-os/claude-md"><img src="https://agentmods.dev/badge/instructions/eigenlegal/counsel-os/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,701 This file is loaded in full into every session.

When invoked 1,701 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01701	$0.01701
Opus 5.5	$0.00680	$0.00680
Sonnet 5.5	$0.00340	$0.00340
Haiku 4.5	$0.00170	$0.00170

Measured 1mo ago against content hash 8e399573b8b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

counsel-os CLAUDE.md 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.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Counsel OS — Developer Guide

This is the source repo for the Counsel OS standalone app and agent plugin. Standalone development is the current priority: a general legal workspace using the five primitives, with matters, knowledge, references, documents, and automatic recordkeeping. The plugin may support a smaller feature set.

Architecture

5 primitives (read, research, evaluate, draft, remember) composed dynamically by the LLM based on user intent. No fixed pipeline or contract-review-only product scope.

Standalone work follows the workspace architecture and the matter-and-knowledge implementation plan. The target uses SQLite for structured app state; the current runtime still uses legacy files, and existing user data must not be migrated incidentally. A shared core, plugin parity, and parallel Markdown/SQL implementations are not prerequisites.

bun run workspace --demo builds and opens the chat-first SQLite workspace with synthetic records; bun run workspace opens a personal workspace. Its service is runtime/src/workspace and its UI is runtime/ui/src/workspace. The native desktop bundles this engine and its document workers. Interface 29/schema 19 includes local chat/preference draft recovery and optional onboarding. Word/PDF operations and ad-hoc local packaging have bounded synthetic qualification; broader fidelity, provider/account qualification, signed distribution and updates remain open. Claude Code runs the user's unmodified CLI with CLI-owned sign-in, explicit billing selection and no copying of subscription credentials. The legacy serve command and UI remain available for existing data; never migrate it incidentally.

For the plugin, /counsel-os:counsel auto-invokes for legal work and contains its orchestrator. See the plugin direction. Reuse content and document tooling where useful; the app's workflow and data model can evolve independently.

Read the full file on GitHub · 94 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.

1mo ago Changed · +13 lines · +427 tokens per session 8e399573b8b5
2mo ago Changed · +6 tokens per session f60dc5f84e51
2mo ago First seen · 81 lines · 1,268 tokens per session scan A 0f91401ff308

Subscribe to this mod's changes

counsel-os CLAUDE.md is an instructions file published in the GitHub repository eigenlegal/counsel-os (25 stars, last pushed 1mo ago), licensed MIT. It adds 1,701 tokens to every session, about $0.0068 per session on Opus 5.5. 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.

Legal and compliance

counsel-os CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
counsel-os CLAUDE.mdeigenlegal/counsel-os	Instructions file	25	1mo ago	MIT	A	1,701	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

counsel-os: Instructions file for Claude Code