holoviz-mcp: Instructions file for Codex

AGENTS.md

holoviz-mcp AGENTS.md is an instructions file for Codex, OpenCode from MarcSkovMadsen/holoviz-mcp. It costs 5,230 tokens per session, scanned C, original, BSD-3-Clause.

Repository instructions for HoloViz MCP, a Python server that gives AI assistants access to Panel, hvPlot, and HoloViz documentation. They describe the project and its required development environment.

In plain words
What is it for?
Use them when contributing to the HoloViz MCP repository, especially when setting up the environment, running tests, or understanding its Python and documentation-related components.
Why use it?
They reduce setup mistakes by documenting the correct tools, commands, project structure, and testing approach before code changes begin.

Instructions file for CodexOpenCode

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/marcskovmadsen/holoviz-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/marcskovmadsen/holoviz-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,230 This file is loaded in full into every session.
When invoked 5,230 The same file — it is already loaded in full.
Security scan C 2 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 $0.05230 $0.05230
Opus 5 $0.02615 $0.02615
Sonnet 5 $0.01046 $0.01046
Haiku 4.5 $0.00523 $0.00523

Measured 9d ago against content hash 1e6d5f072a86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

holoviz-mcp AGENTS.md scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://pixi.sh/install.sh | bash

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://pixi.sh/install.sh | bash
AGENTS.md · 720 lines

How it starts

The opening of the file, as written. The whole thing — 720 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - HoloViz MCP Server

A README for AI coding agents to effectively contribute to the HoloViz MCP project.


Repository Overview

Project: HoloViz MCP - Model Context Protocol server for the HoloViz ecosystem Purpose: Provides AI assistants with intelligent access to Panel, hvPlot, and HoloViz documentation Language: Python 3.11+ Build System: Pixi (conda-based) + Hatchling (PEP 517) Framework: FastMCP (Python MCP SDK) Key Dependencies: ChromaDB, sentence-transformers, Panel

Project Statistics

  • Source Files: ~20 Python modules in src/holoviz_mcp/
  • Test Coverage: Unit tests, integration tests, and UI tests (Playwright)
  • Total Dependencies: ~240 packages (includes ML/AI dependencies)
  • Platforms: macOS (ARM64/x64), Linux (x64/ARM64), Windows (x64)

Quick Start - ALWAYS RUN FIRST

Environment Setup

CRITICAL: This project uses Pixi for reproducible environments. DO NOT use pip/conda directly.

# 1. Install Pixi (if not already installed)
curl -fsSL https://pixi.sh/install.sh | bash

# 2. Clone and enter the repository
cd holoviz-mcp

# 3. Install development environment
pixi install

# 4. Install pre-commit hooks (MANDATORY BEFORE ANY COMMITS)
pixi run pre-commit-install

# 5. Install the package in editable mode
pixi run postinstall

Expected output: Environment should install ~240 packages. First run takes 5-10 minutes.

Verification

# Verify installation
pixi run holoviz-mcp --help

# Run tests to ensure everything works
pixi run test

# ✓ All tests should pass on a clean checkout

Pre-Commit Hooks - MANDATORY BEFORE PRs

ALWAYS RUN before committing or creating pull requests:

pixi run pre-commit-run
# ✓ Takes 1-3 minutes on first run (installs hook environments)
# ✓ Subsequent runs are fast (<30 seconds)
# ✓ Auto-fixes many issues (formatting, imports, trailing whitespace)

What Gets Checked

  • Ruff: Import sorting (isort), formatting, linting
  • MyPy: Type checking
  • Prettier: CSS/JSON/YAML formatting
  • Codespell: Spell checking
  • Pre-commit hooks: Trailing whitespace, end-of-file, TOML/JSON validation
  • Clean notebook: Jupyter notebook cleaning

Read the full file on GitHub · 720 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. 9d ago First seen · 720 lines · 5,230 tokens per session scan C 1e6d5f072a86

Subscribe to this mod's changes

holoviz-mcp AGENTS.md is an instructions file published in the GitHub repository MarcSkovMadsen/holoviz-mcp (34 stars, last pushed 8d ago), licensed BSD-3-Clause. It adds 5,230 tokens to every session, about $0.0261 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens