What is orangepro-mcp CLAUDE.md?

A repository instruction guide explains two OrangePro products: a local command-line and MCP server for testing code, and a hosted MCP server for managing agents and quality analysis. MCP is a standard way for AI assistants to call tools provided by another program.

Use it when building, testing, or changing the OrangePro repository, including its evidence graph, generated tests, mutation checks, agent management, and QA analysis.

It gives coding agents the project’s architecture, commands, and boundaries before they make changes. This helps avoid confusing the local product with the hosted service.

How OrangeproAI/orangepro-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OrangeproAI/orangepro-mcp. 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/OrangeproAI/orangepro-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/OrangeproAI/orangepro-mcp

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/orangeproai/orangepro-mcp/claude-md.svg)](https://agentmods.dev/instructions/orangeproai/orangepro-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/orangeproai/orangepro-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/orangeproai/orangepro-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,224 This file is loaded in full into every session.

When invoked 1,224 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	$0.01224	$0.01224
Opus 5	$0.00612	$0.00612
Sonnet 5	$0.00245	$0.00245
Haiku 4.5	$0.00122	$0.00122

Measured 7d ago against content hash b3832e6ca5ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

orangepro-mcp 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 7d 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 · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 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.

What This Is

Two independent products live here (they share no code):

OrangePro Local Proof Kit (src/local/**, bin opro, alias orangepro-local) — the product the npm package ships. A local-first CLI + MCP server that builds an OrangePro-shaped evidence graph from a local checkout, scores readiness, generates grounded tests via BYOK model adapters, dynamically proves behaviors via a mutation oracle (TS/JS, Go, Java, Python), and exports a metadata-only evidence pack. It does NOT call the hosted API. See docs/local-proof-kit.md.
OrangePro MCP server (src/index.ts + top-level src/*.ts) — a Model Context Protocol server that exposes OrangePro's hosted agent platform and QA intelligence APIs as MCP tools over stdio. Clients (Claude Desktop, Claude Code, etc.) connect and call tools to manage OrangePro agents, resolve stories against a Knowledge Graph, and run QA analytics (coverage gaps, PR risk, release readiness, bug-to-test conversion, test generation). Requires a hosted backend; not part of the npm package.

Commands

npm run build        # tsc → dist/ (emits both bins via tsconfig.build.json)
npm run dev          # tsx src/index.ts (hosted server, stdio, needs MCP client)
npm run start        # node dist/index.js (requires build first)
npm test             # full sharded suite; Go/Java/Python chunks skip when the toolchain is absent
npm run test:rest    # fast TS-only lane (excludes the language proof spikes)
npm run typecheck    # tsc --noEmit

Single test file: npx vitest run tests/config.test.ts

Local proof kit: npm run local -- analyze . (dev), node scripts/smoke-local.mjs (offline e2e smoke). Other smoke lanes: npm run smoke:generate-prove, smoke:generate-prove-v5, smoke:db-sqljs, smoke:gap-fill.

Environment

Hosted MCP server (set in your environment or a local .env):

ORANGEPRO_API_BASE_URL — backend API (default: http://localhost:8000/api/v1)
ORANGEPRO_TENANT_ID — default tenant; most tools accept an optional tenant_id override
ORANGEPRO_API_KEY — bearer token sent as both Authorization and X-API-Key
ORANGEPRO_USER_EMAIL — sent as X-User-Email header
ORANGEPRO_ORGANIZATION_NAME — sent as X-Organization-Name header (falls back to tenant ID)

Read the full file on GitHub · 65 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.

7d ago First seen · 65 lines · 1,224 tokens per session scan A b3832e6ca5ee

Subscribe to this mod's changes

orangepro-mcp CLAUDE.md is an instructions file published in the GitHub repository OrangeproAI/orangepro-mcp (17 stars, last pushed 2d ago), licensed MIT. It adds 1,224 tokens to every session, about $0.0061 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.

Claude Code ai-test-generator ai-testing behavioral-coverage code-coverage developer-experience

graftcode copilot-instructions.md

Copilot instructions for grft-dev/graftcode, covering graftcode — default integration policy (router), pre-flight — do this before writing any backend code, core policy (always), universal graftcode rules (every language) and hosting: docker containers or local gg (ask if unspecified).

grft-dev/graftcode · 6,921 tokens

graftcode graftcode-dotnet.instructions.md

Instructions for grft-dev/graftcode, covering graftcode — .net backend services, when this applies (always), authoritative docs (source of truth), golden rules and service = .net class library.

grft-dev/graftcode · 7,060 tokens

graftcode graftcode-python.instructions.md

Instructions for grft-dev/graftcode, covering graftcode — python backend services, when this applies (always), authoritative docs (source of truth), golden rules and service = plain python module (no web framework).

grft-dev/graftcode · 4,639 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

orangepro-mcp: Instructions file for Claude Code