What is liam CLAUDE.md?

A repository instruction file for the Liam project covering common commands, application locations, package structure, and development guidance. A monorepo is one repository that contains several applications and reusable packages.

Use it to work on Liam’s web apps, documentation site, command-line tool, visualization packages, schema tools, and internal agent package.

It gives coding agents a shared reference for running the right development, build, test, lint, and formatting commands.

liam CLAUDE.md — Instructions file by liam-hq

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 instructions/liam-hq/liam/claude-md

Clone the repo

git clone --depth 1 https://github.com/liam-hq/liam

Per session 945 This file is loaded in full into every session.

When invoked 945 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00945	$0.00945
Opus 5	$0.00473	$0.00473
Sonnet 5	$0.00189	$0.00189
Haiku 4.5	$0.00094	$0.00094

Measured yesterday against content hash e4c3f3e1deeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

liam 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 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.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 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.

Essential Commands

pnpm dev - Start dev servers
cd frontend/apps/app && pnpm dev - Start dev server for specific package
pnpm build - Build all packages
pnpm lint - Run linting and formatting
pnpm test - Run tests
pnpm fmt - Run format code

App-specific Commands

# Run only the main web app (port 3001)
pnpm --filter @liam-hq/app dev

# Format code
pnpm --filter @liam-hq/agent fmt

# Test
pnpm --filter @liam-hq/agent test

Architecture

Monorepo Structure

Applications

frontend/apps/app - Main Next.js web application (@liam-hq/app)
frontend/apps/docs - Documentation site (@liam-hq/docs)

Public Packages

frontend/packages/cli - Command-line tool (@liam-hq/cli)
frontend/packages/erd-core - Core ERD visualization (@liam-hq/erd-core)
frontend/packages/schema - Database schema parser (@liam-hq/schema)
frontend/packages/ui - UI component library (@liam-hq/ui)

Internal Packages

frontend/internal-packages/agent - AI agent system using LangGraph (@liam-hq/agent)
frontend/internal-packages/db - Database utilities (@liam-hq/db)
frontend/internal-packages/mcp-server - MCP server implementation (@liam-hq/mcp-server)

Key Technologies

Frontend: React 19, Next.js 15, TypeScript
Styling: CSS Modules with typed definitions
Visualization: @xyflow/react (React Flow)
Validation: Valibot for runtime type validation
Build: Turborepo, pnpm workspaces

Development Guidelines

Core Principle: Less is more

Keep every implementation as small and obvious as possible.

Let the code speak – If you need a multi-paragraph comment, refactor until intent is obvious
Delete fearlessly, Git remembers – Cut dead code, stale logic, and verbose history

TypeScript Standards

Use runtime type validation with valibot for external data validation
Use early returns for readability

Read the full file on GitHub · 121 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.

yesterday First seen · 121 lines · 945 tokens per session scan A e4c3f3e1deeb

Subscribe to this mod's changes

liam CLAUDE.md is an instructions file published in the GitHub repository liam-hq/liam (5,100 stars, last pushed 3d ago), licensed Apache-2.0. It adds 945 tokens to every session, about $0.0047 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.

Databases Writing and docs data-visualization database-schema documentation documentation-tool entity-relationship-diagram

liam CLAUDE.md