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/sixhq/overture/claude-mdgit clone --depth 1 https://github.com/SixHq/OvertureWrote 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/sixhq/overture/claude-md)<a href="https://agentmods.dev/instructions/sixhq/overture/claude-md"><img src="https://agentmods.dev/badge/instructions/sixhq/overture/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 | $0.01450 | $0.01450 |
| Opus 5 | $0.00725 | $0.00725 |
| Sonnet 5 | $0.00290 | $0.00290 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
Overture 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 5d 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 — 148 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.
Project Overview
Overture is an MCP (Model Context Protocol) server that provides visual plan execution and approval workflows for AI coding agents. It intercepts AI agent planning phases and renders them as interactive visual flowcharts before code is written. Works with Claude Code, Cursor, Cline, GitHub Copilot, and Sixth AI.
Monorepo Structure
This is an npm workspaces monorepo with two packages:
packages/mcp-server- The MCP server (Node.js/TypeScript)packages/ui- The React frontend (React Flow + Zustand + Tailwind)
Build & Development Commands
# Install dependencies (from root)
npm install
# Development - runs both server and UI with hot reload
npm run dev
# Build all packages for production
npm run build
# Development - individual packages
npm run dev:server # MCP server only (tsx watch)
npm run dev:ui # UI only (vite dev server)
# Build - individual packages
npm run build:server # Outputs to packages/mcp-server/dist/
npm run build:ui # Outputs to packages/mcp-server/ui-dist/
# Production start
npm start # Runs built MCP server
# Clean all build artifacts
npm run clean
MCP Server Package Commands
cd packages/mcp-server
npm run dev # tsx watch src/index.ts
npm run build # tsup to dist/
npm run lint # eslint src/**/*.ts
npm run start # node dist/index.js
UI Package Commands
cd packages/ui
npm run dev # vite dev server
npm run build # tsc && vite build
npm run preview # vite preview
Architecture
MCP Server (packages/mcp-server/src/)
Entry Points:
index.ts- MCP server initialization using@modelcontextprotocol/sdk, starts HTTP (3031) and WebSocket (3030) serverscli.ts- CLI entry point fornpx overture-mcp
Core Modules:
tools/handlers.ts- Implements all 11 MCP tools (submit_plan,get_approval,update_node_status, etc.)store/plan-store.ts-MultiProjectPlanStoremanages plans across multiple projects with Promise-based approval flowwebsocket/ws-server.ts-WebSocketManagerhandles client connections, project subscriptions, and relay modehttp/server.ts- Express server serving UI and API endpoints (/api/test-plan,/api/mcp-marketplace)parser/xml-parser.ts- SAX-basedStreamingXMLParserfor parsing plan XML into nodes/edgesparser/output-parser.ts- Parses structured output from agent executionstorage/history-storage.ts- Persists plans to~/.overture/history.jsontypes.ts- Core types:PlanNode,PlanEdge,Plan,ProjectContext,WSMessageutils/plan-diff.ts- Computes differences between plan versions
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.
- 5d ago First seen · 148 lines · 1,450 tokens per session scan A a745e73ebb97
Overture CLAUDE.md is an instructions file published in the GitHub repository SixHq/Overture (635 stars, last pushed 6mo ago), licensed MIT. It adds 1,450 tokens to every session, about $0.0072 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.
Other instructions, from other repositories
memorix CLAUDE.md
Claude Code instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
memorix GEMINI.md
Gemini CLI instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
Ctxo CLAUDE.md
Claude Code instructions for alperhankendi/Ctxo, covering claude.md — ctxo, project overview, quick reference, dev (pnpm workspace) and usage (consumer).
draft CLAUDE.md
Instructions for drafthq/draft, covering claude.md, repository overview, build & test commands, run a single test and etc. — any test in tests/ is independently executable.
Ctxo copilot-instructions.md
Copilot instructions for alperhankendi/Ctxo, covering ctxo mcp tool usage (mandatory), before any code modification, before starting a task, before reviewing a pr or diff and when exploring or searching code.
specops CLAUDE.md
Instructions for sanmak/specops, covering claude.md, what is specops, build & validate commands, run all tests (single command) and generate for a single platform.