octoparse-mcp: Instructions file for Codex

AGENTS.md

octoparse-mcp AGENTS.md is an instructions file for Codex, OpenCode from octoparse/octoparse-mcp. It costs 5,588 tokens per session, scanned A, original, MIT.

A project instruction file for AI coding agents working on OctopusMCPServer, a TypeScript server that exposes Octoparse capabilities through MCP. It explains the project's purpose, architecture, priorities, and development rules.

In plain words
What is it for?
Use it as the repository's agent guide during development, code changes, documentation work, and conflict resolution. It provides project context and directs agents to the relevant instructions for different tasks.
Why use it?
It gives agents a shared starting point before they change code or documentation. This helps them understand which files to read, what the project values, and how to resolve conflicts when instructions and code differ.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/octoparse/octoparse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/octoparse/octoparse-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,588 This file is loaded in full into every session.
When invoked 5,588 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 $0.05588 $0.05588
Opus 5 $0.02794 $0.02794
Sonnet 5 $0.01118 $0.01118
Haiku 4.5 $0.00559 $0.00559

Measured 12d ago against content hash 776c9a9ba7cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

octoparse-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 12d 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 · 848 lines

How it starts

The opening of the file, as written. The whole thing — 848 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Agent Guide

This document is the unified working guide for AI coding agents in OctopusMCPServer.

It applies to:

  • Codex
  • Claude Code
  • Gemini
  • Any other AI agent that reads code, changes code, writes documentation, or resolves conflicts in this repository

This file is intended to be the foundation for future development of this project. An agent should be able to use it to quickly establish a consistent understanding of:

  • what this project is
  • what the current runtime architecture is
  • what the project actually values
  • which constraints must not be broken
  • which files should be read first before different kinds of changes
  • which direction should be preferred during merge conflict resolution

If this document conflicts with the current code, the current code wins. If this document becomes outdated, update it as part of the same change.


1. Project Identity

OctopusMCPServer is a TypeScript-based MCP server. It exposes Octoparse-related capabilities over HTTP for MCP clients.

This repository is not just a flat list of tools and not just a thin API wrapper. The current codebase includes several important responsibilities that must be treated as first-class architecture:

  • an Express 5 HTTP server
  • MCP over Streamable HTTP
  • session creation, recovery, and deletion
  • dual authentication entry points through JWT and API key
  • request-scoped context built on AsyncLocalStorage
  • downstream Octoparse API access and HTTP connection pooling
  • tool middleware chains
  • structured logging and secure error handling
  • optional Redis-backed persistence
  • LLM-oriented tool interface design

The core value of this repository is not only "making the API work." Its real value is:

  • correctly implementing MCP protocol behavior
  • correctly isolating authentication context across users and requests
  • correctly recovering distributed sessions
  • correctly converging complex business capabilities into tool interfaces that LLMs can understand, choose, and recover from

Read the full file on GitHub · 848 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. 12d ago First seen · 848 lines · 5,588 tokens per session scan A 776c9a9ba7cd

Subscribe to this mod's changes

octoparse-mcp AGENTS.md is an instructions file published in the GitHub repository octoparse/octoparse-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 5,588 tokens to every session, about $0.0279 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.

Related

Other instructions, from other repositories

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

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

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