Borrowing it
Nothing to install: this file belongs to jessepike/diagram-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jessepike/diagram-forge/main/CLAUDE.mdgit clone --depth 1 https://github.com/jessepike/diagram-forgeWrote 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.
[](https://agentmods.dev/instructions/jessepike/diagram-forge/claude-md)<a href="https://agentmods.dev/instructions/jessepike/diagram-forge/claude-md"><img src="https://agentmods.dev/badge/instructions/jessepike/diagram-forge/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00780 | $0.00780 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
diagram-forge 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Forge — MCP Server
Project Overview
Standalone MCP server for generating enterprise-grade architecture diagrams via AI image providers (Google Gemini, OpenAI GPT Image). Pip-installable, cross-client compatible (Claude Code, Claude Desktop, Codex CLI, Gemini CLI).
Architecture
- Framework: FastMCP (mcp>=1.0.0) with stdio transport
- Layout: src/diagram_forge/ — standard src layout
- Providers: Swappable via BaseImageProvider ABC (providers/)
- Templates: YAML-based prompt templates (templates/)
- Styles: Reference image management (styles/)
- Cost tracking: SQLite-backed usage/cost database
- Config: YAML + env vars + Pydantic validation
Conventions
- Python 3.11+, Pydantic v2 with ConfigDict
- Async throughout (provider calls, MCP tools)
- Type hints on all public APIs
- Tests in tests/ with pytest-asyncio
- Ruff for linting, mypy for type checking
Key Files
src/diagram_forge/server.py— FastMCP tool registration (entry point)src/diagram_forge/models.py— All Pydantic modelssrc/diagram_forge/config.py— Config loading + validationsrc/diagram_forge/providers/base.py— Provider ABCconfig/default_config.yaml— Default configurationconfig/pricing.yaml— Provider pricing rates
Claude Code Plugin
The diagram-forge-plugin/ directory contains a Claude Code plugin with:
- Commands:
/diagram:create,/diagram:iterate,/diagram:usage,/diagram:templates - Agent:
context-gatherer— explores project architecture - Skill:
diagram-intelligence— auto-triggers on diagram requests
Style System
Styles live in two places:
- Bundled:
src/diagram_forge/styles/<name>/— checked into repo - User:
~/.diagram-forge/styles/<name>/— personal styles, not in repo
Each style dir needs: reference.png (visual reference) + style.yaml (name, display_name, description, tags).
The description field is injected as text into every prompt when the style is used by name. The reference.png is passed visually via images.edit for OpenAI or as image input for Gemini.
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.
- 6d ago First seen · 80 lines · 780 tokens per session scan A 8daab7457dd8
diagram-forge CLAUDE.md is an instructions file published in the GitHub repository jessepike/diagram-forge (1 stars, last pushed 1mo ago), licensed MIT. It adds 780 tokens to every session, about $0.0039 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
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.
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.
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).
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).
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.
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.