mineru-tianshu: Instructions file for Claude Code

CLAUDE.md

mineru-tianshu CLAUDE.md is an instructions file for Claude Code from magicyuan876/mineru-tianshu. It costs 2,100 tokens per session, scanned A, original, Apache-2.0.

Project guidance for MinerU Tianshu, an AI data-processing platform that converts documents and media into Markdown and structured JSON. It covers the project, Docker deployment, local development, and available commands.

In plain words
What is it for?
Use it when changing MinerU Tianshu, especially its Vue frontend, FastAPI server, GPU workers, task queues, or Docker setup.
Why use it?
It gives the coding agent the repository context and the commands needed to build, run, test, and manage the platform.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is magicyuan876/mineru-tianshu's own configuration. It tells Claude Code how to work on mineru-tianshu itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mineru-tianshu configures →

Reuse

Borrowing it

Nothing to install: this file belongs to magicyuan876/mineru-tianshu. 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/magicyuan876/mineru-tianshu/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/magicyuan876/mineru-tianshu

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.

agentmods badge for mineru-tianshu CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/magicyuan876/mineru-tianshu/claude-md/github.svg)](https://agentmods.dev/instructions/magicyuan876/mineru-tianshu/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/magicyuan876/mineru-tianshu/claude-md"><img src="https://agentmods.dev/badge/instructions/magicyuan876/mineru-tianshu/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mineru-tianshu CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/magicyuan876/mineru-tianshu/claude-md"><img src="https://agentmods.dev/badge/instructions/magicyuan876/mineru-tianshu/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,100 This file is loaded in full into every session.
When invoked 2,100 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02100 $0.02100
Opus 5 $0.01050 $0.01050
Sonnet 5 $0.00420 $0.00420
Haiku 4.5 $0.00210 $0.00210

Measured today against content hash 48a231875483, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mineru-tianshu 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 today.

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 · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 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

MinerU Tianshu (天枢) — an AI data preprocessing platform that turns PDFs, Office docs, images, audio, video and bioinformatics files into Markdown + structured JSON. Vue 3 frontend, FastAPI API server, LitServe GPU worker pool, SQLite task queue, optional Redis queue / MCP server / RustFS object storage.

Code comments, logs and docs are predominantly Simplified Chinese — match that when editing existing files.

Commands

Docker (primary deployment path)

make setup           # first-time: runs setup.sh (interactive deployment wizard)
make build | start | stop | restart | status | logs
make logs-worker     # per-service logs (also logs-backend, logs-frontend)
make shell-worker    # exec into a container
make test-gpu        # verify torch CUDA inside the worker
make validate        # docker compose config
make dev             # docker-compose.dev.yml (hot reload + debugpy)

make reads REDIS_QUEUE_ENABLED from the root .env and adds --profile redis when true. setup.sh (repo root) is the single deployment entry: bash setup.sh (interactive), or bash setup.sh --mode <gpu|pipeline|cpu|offline-build|offline-deploy|dev> [--gpus N] [--concurrency N] [--yes] [--dry-run]. Offline/air-gapped: --mode offline-build on a connected machine (bundle in docker-images/), then --mode offline-deploy on the target. Mac CPU local dev: --mode cpu.

Local backend

cd backend
cp .env.example .env          # REQUIRED — start_all.py exits if backend/.env is missing
python start_all.py                       # API 8000 + worker 8001
python start_all.py --enable-mcp --mcp-port 8002
python start_all.py --workers-per-device 2 --devices 0,1 --accelerator cuda

All backend processes must run with backend/ as CWD (imports are top-level: from utils import ..., from auth import ...). Individual services: python api_server.py, python litserve_worker.py, python task_scheduler.py --enable-scheduler, python mcp_server.py.

Read the full file on GitHub · 172 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.

  1. today Changed · +1 lines · +28 tokens per session 48a231875483
  2. 12d ago First seen · 171 lines · 2,072 tokens per session scan A 9a6614ea7a1e

Subscribe to this mod's changes

mineru-tianshu CLAUDE.md is an instructions file published in the GitHub repository magicyuan876/mineru-tianshu (797 stars, last pushed yesterday), licensed Apache-2.0. It adds 2,100 tokens to every session, about $0.0105 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.

Related

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.

vercel/next.js · 7,296 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 · 5,153 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

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.

github/spec-kit · 7,126 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens