mineru-mcp: Instructions file for Codex

AGENTS.md

mineru-mcp AGENTS.md is an instructions file for Codex, OpenCode from linxule/mineru-mcp. It costs 2,365 tokens per session, scanned A, original, MIT.

A contributor handoff guide for the MinerU MCP TypeScript package. It records the project's verified baseline, important repository rules, runtime details, and limits on what the published package version supports.

In plain words
What is it for?
Use it when changing the package, checking its status, reviewing verification results, understanding runtime support, or handing work to another contributor.
Why use it?
It helps contributors distinguish the current source tree from older published packages and avoid treating local tests or dated checks as proof of live provider behavior. It also points to the files and commands that define the project's workflow.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is linxule/mineru-mcp's own configuration. It tells Codex and OpenCode how to work on mineru-mcp 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-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to linxule/mineru-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/linxule/mineru-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/linxule/mineru-mcp

Made for: Codex, OpenCode.

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-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/linxule/mineru-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/linxule/mineru-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/linxule/mineru-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/linxule/mineru-mcp/agents-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-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/linxule/mineru-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/linxule/mineru-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,365 This file is loaded in full into every session.
When invoked 2,365 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 $0.02365 $0.02365
Opus 5.5 $0.00946 $0.00946
Sonnet 5.5 $0.00473 $0.00473
Haiku 4.5 $0.00236 $0.00236

Measured 1mo ago against content hash 72221abf9479, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mineru-mcp AGENTS.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 1mo 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.

AGENTS.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributor handoff

This is the canonical contributor guide for this independent TypeScript package. Apply higher-level instructions too. Read README.md for user workflows and the actual tool schemas before changing behavior. CLAUDE.md points here.

Verified baseline and authority

As of 2026-09-30, pushed main is 49e88ca (portable verification/release gates), including 9d3c95e (provider boundaries, durable recovery, artifact containment). Package/server versions remain 1.2.0. The published npm 1.2.0 predates the new durable-operation and bundle features; a clean checkout or passing package test does not make those features available from npm.

Last verification: build passed, full suite 323/323, fresh consumer package on Node 18.20.8 8/8, and publication-version guard fixtures 7/7. These are dated synthetic/offline checks, not a live provider pilot or parsing-accuracy claim. Local full-suite execution used macOS/Node 26; CI is configured for Node 24 on macOS/Linux and fresh-package checks on Node 18 on both platforms. Ordinary main pushes now run verification only. Publishing still requires a version tag; manual dispatch remains registry recovery for an existing release tag and must not be used as a verification-only trigger. A pushed commit alone does not establish a hosted CI pass; inspect the run for that exact commit.

Check git status --short before work; preserve unrelated edits and other agents' ownership. Keep work local unless the task authorizes more. Documentation, tests, and local builds do not authorize provider calls, credential access, push, tags, npm publication, or registry registration. A partially failed or uncertain cloud request is not permission to submit again.

Runtime and code map

Use Bun 1.4.2 for dependency/build commands. Recommend Node 24; retain Node >=18 runtime compatibility. bun.lock owns locked dependency resolution. dist/ is generated and ignored; rebuild before running tests or the CLI. Keep the MCP SDK 1.29.x compatibility bound until the fresh Node 18 consumer gate proves a change.

Read the full file on GitHub · 186 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. 1mo ago Changed · +17 lines · +237 tokens per session 72221abf9479
  2. 1mo ago First seen · 169 lines · 2,128 tokens per session scan A 12b0a8794c2b

Subscribe to this mod's changes

mineru-mcp AGENTS.md is an instructions file published in the GitHub repository linxule/mineru-mcp (10 stars, last pushed 5d ago), licensed MIT. It adds 2,365 tokens to every session, about $0.0095 per session on Opus 5.5. 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 2026-10-02.

Related

mineru-mcp AGENTS.md compared with instructions from other repositories

mineru-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mineru-mcp AGENTS.mdlinxule/mineru-mcpInstructions file105d agoMITA2,365Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode