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.
npx agentmods add instructions/liam-machine/erd-studio/claude-mdgit clone --depth 1 https://github.com/liam-machine/erd-studioWhat 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 | $0.04137 | $0.04137 |
| Opus 5 | $0.02069 | $0.02069 |
| Sonnet 5 | $0.00827 | $0.00827 |
| Haiku 4.5 | $0.00414 | $0.00414 |
Grade A, and why
erd-studio 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 315 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.
Naming
The extension display name is ERD Studio (package name erd-studio).
Directory Structure
ERD domain files live at {project_root}/.erd-studio/{layer}/{domain}.json. Each file is a unified domain containing the logical stage data. The custom editor activates for files matching:
**/.erd-studio/*/*.json
The base directory is configurable via the erdStudio.semanticDir setting (default: .erd-studio).
.erd-studio/
├── layers.json
├── templates/
├── silver/
│ ├── customer-360.json ← domain file (logical stage)
│ └── orders.json
└── gold/
└── reporting.json
Internal Identifiers
All internal identifiers use the erdStudio prefix (erd-studio for the activity bar container id), with the command palette category "ERD Studio". The extension was originally published with a dbtSemantic prefix; two compatibility shims keep pre-rename users working and must not be removed:
- Legacy command aliases: every
erdStudio.*command is also registered in code asdbtSemantic.*(seeLEGACY_ALIASED_COMMANDSat the end ofactivate()insrc/extension.ts) so old keybindings keep working. These are code-only registrations — never contribute them in package.json. - Legacy setting fallback: settings are read via
getErdStudioSetting()(src/services/configService.ts), which prefers expliciterdStudio.*values and falls back to explicitdbtSemantic.*values. The deprecateddbtSemantic.projectPath/dbtSemantic.semanticDirentries in package.json carrymarkdownDeprecationMessageand must stay contributed. Never read settings withgetConfiguration('erdStudio').get(...)directly — always use the helper.
Build & Test Commands
npm run build # Build both extension + webview bundles (esbuild)
npm run watch # Watch mode — rebuilds on change
npm run compile # Type-check only (both tsconfigs, no emit)
npm run test # Run unit tests (vitest)
npm run test:watch # Run tests in watch mode
npm run package # Production build (minified, no sourcemaps)
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.
- 2d ago First seen · 315 lines · 4,137 tokens per session scan A b0b990e9ceb1
erd-studio CLAUDE.md is an instructions file published in the GitHub repository liam-machine/erd-studio (5 stars, last pushed 2mo ago), licensed MIT. It adds 4,137 tokens to every session, about $0.0207 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 2026-08-31.
Other instructions, from other repositories
docglow CLAUDE.md
Instructions for docglow/docglow, covering claude.md — docglow, project, tech stack, build & test and python.
dbt-doctor AGENTS.md
Instructions for northgraindata/dbt-doctor, covering dbt-doctor, stack, commands and conventions.
fabric-dw-mcp-cli CLAUDE.md
Instructions for sdebruyn/fabric-dw-mcp-cli, covering claude.md and no sql parsing.
foggy-data-mcp-bridge-python CLAUDE.md
Instructions for foggy-projects/foggy-data-mcp-bridge-python, covering foggy data mcp bridge — python, 快速启动, 安装依赖, 运行测试 and 启动 mcp 服务(连接 docker mysql).
ade-bench-plugin CLAUDE.md
Instructions for typedef-ai/ade-bench-plugin, covering claude.md, what this repository is, repository layout and how the pieces interact and key invariants when editing skills or templates.
ai-workflow AGENTS.md
Instructions for cunhaax/ai-workflow, covering ai workflow template, rules — non-negotiable, project overview, commands and architecture.