open-notebook-mcp AGENTS.md

open-notebook-mcp AGENTS.md is an instructions file for Codex, OpenCode from Epochal-dev/open-notebook-mcp. It costs 3,133 tokens per session, scanned A, original, MIT.

Repository instructions for building open-notebook-mcp, a Python MCP server that lets an agent use external tools or data. They define how capabilities should be discovered and how results should be kept small.

In plain words
What is it for?
Use them when designing or implementing MCP tools, capability search, summaries with references, stable schemas, and STDIO or HTTP deployment.
Why use it?
They reduce unnecessary information in the agent’s working context and make the server’s tools, outputs, errors, and deployment behavior predictable.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/epochal-dev/open-notebook-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/Epochal-dev/open-notebook-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 open-notebook-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/epochal-dev/open-notebook-mcp/agents-md.svg)](https://agentmods.dev/instructions/epochal-dev/open-notebook-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/epochal-dev/open-notebook-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/epochal-dev/open-notebook-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,133 This file is loaded in full into every session.
When invoked 3,133 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.03133 $0.03133
Opus 5 $0.01566 $0.01566
Sonnet 5 $0.00627 $0.00627
Haiku 4.5 $0.00313 $0.00313

Measured 3d ago against content hash e8b87d134b82, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open-notebook-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 3d 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 · 446 lines

How it starts

The opening of the file, as written. The whole thing — 446 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — MCP Server Best Practices (Python / FastMCP) — Codex-First

This file is the operating manual for an agent (Codex) that implements MCP servers in Python. Goal: MCP servers that are discoverable on-demand, context-efficient, predictable, testable, and deployable over STDIO and Streamable HTTP.

Core idea: avoid stuffing every tool definition + every intermediate result into the model context. Prefer progressive disclosure and compute/filter in the execution environment, returning compact results.


1) Prime directive: context efficiency > everything

  1. Default to small outputs. If it might be big, return a summary + handle (cursor/id/path).
  2. Filter/transform server-side. Don’t stream 10,000 rows into the model just to filter them.
  3. Progressive disclosure is mandatory. Every server must implement search_capabilities(...) with a detail level.
  4. Prefer composable tools. Many small orthogonal tools beat one mega-tool.
  5. Deterministic behavior. Stable error codes, stable schemas, stable names.

2) Hard requirement: standardized progressive disclosure

You are standardizing a discovery pattern across all MCP servers:

2.1 Required tool: search_capabilities

Contract

  • Inputs:
    • query: str (free text)
    • detail: Literal["name","summary","full"] = "summary"
    • limit: int = 20 (server-enforced max, e.g. 50)
  • Output (JSON object):
    • matches: list[CapabilityMatch]
    • count: int
    • hint: str | None (optional “try these queries/tags”)

Detail levels

  • name: tool names only
  • summary: name + one-liner + tags
  • full: summary + parameters + return shape + 1 example call + typical output size

Why

  • Lets Codex find just what it needs without loading every tool definition.
  • Lets you keep tool descriptions minimal and stable.

2.2 Optional but strong: manifest resource

Expose a small read-only “server manifest” resource for metadata (name/version/base_url/tags). Use it for humans and debugging, not as a substitute for search_capabilities.

Read the full file on GitHub · 446 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. 3d ago First seen · 446 lines · 3,133 tokens per session scan A e8b87d134b82

Subscribe to this mod's changes

open-notebook-mcp AGENTS.md is an instructions file published in the GitHub repository Epochal-dev/open-notebook-mcp (43 stars, last pushed 8mo ago), licensed MIT. It adds 3,133 tokens to every session, about $0.0157 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

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 · 7,104 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

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 · 4,345 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

next.js 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