docs-mcp-server AGENTS.md

A repository-specific instruction guide for a documentation server built with Node.js and TypeScript. It explains the project context, development process, required tools, and common commands.

In plain words
What is it for?
It helps with setup, building, linting, formatting, type checking, testing, reading the project documentation, and following its architecture and Git workflow.
Why use it?
It gives a coding agent the background and working rules needed to make changes that fit the repository.

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/arabold/docs-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/arabold/docs-mcp-server

Made for: Codex, OpenCode.

Per session 2,284 This file is loaded in full into every session.
When invoked 2,284 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 $0.02284 $0.02284
Opus 5 $0.01142 $0.01142
Sonnet 5 $0.00457 $0.00457
Haiku 4.5 $0.00228 $0.00228

Measured 2d ago against content hash 4195936bd49f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-mcp-server 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 2d 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 · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions for docs-mcp-server

Repository Context

  • Repository: arabold/docs-mcp-server
  • Core Stack: Node.js 22.x, TypeScript, Vite, AlpineJS, TailwindCSS, SQLite (better-sqlite3)
    • Node Version: Always use Node.js v22 for local development and builds, even if package.json allows older versions. If nvm is installed, run nvm use 22 before local commands.
  • Tooling: Biome (lint/format), Vitest (test), Husky (pre-commit)
  • Critical Documentation:
    • 📖 Read README.md first for project structure, setup, and configuration details.
    • 🏗️ Read ARCHITECTURE.md before making changes to understand system design and service interactions.

Development Workflow

Key Commands

Task Command Description
Setup npm install Install dependencies
Build npm run build Build both server and web assets
Lint npm run lint Check code issues with Biome
Fix npm run lint:fix Auto-fix lint issues (add -- --unsafe if needed)
Typecheck npm run typecheck Run TypeScript compiler checks
Format npm run format Format code with Biome
Test All npm test Run all tests with Vitest
Test Single npx vitest run <path> Run a specific test file (e.g., src/utils/foo.test.ts)

Git Workflow

  • Branching: <type>/<issue>-<desc> (e.g., feat/123-add-cache)
  • Pre-commit: Husky runs lint, typecheck, and tests. Never bypass.
  • Security: NEVER commit secrets, credentials, or sensitive data (e.g., .env).

Dependency Hygiene

  • Use npm ci (not npm install) when you just need node_modules; it installs from the lockfile without mutating it. Reserve npm install for intentional dependency changes.
  • Keep Node 22 — better-sqlite3 ships a Node-ABI-pinned native binary. Do not bump the engine floor to v24+.
  • For occasional CLI tools that aren't part of the runtime (e.g. promptfoo for search evals), invoke them via npx -y <pkg>@<version> from package.json scripts rather than declaring them as dependencies — keeps the dep tree and lockfile clean.
  • npm 10 does not record libc in package-lock.json, so npm ci on Linux installs both the glibc and musl builds of every prebuilt native package (@xberg-io/xberg, @biomejs/cli, lightningcss, …). The Dockerfile prunes the musl copies after npm ci. If the lockfile is ever regenerated from scratch with npm 11+, the libc fields appear and that prune becomes redundant.

Read the full file on GitHub · 139 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. 2d ago First seen · 139 lines · 2,284 tokens per session scan A 4195936bd49f

Subscribe to this mod's changes

docs-mcp-server AGENTS.md is an instructions file published in the GitHub repository arabold/docs-mcp-server (1,701 stars, last pushed 4d ago), licensed MIT. It adds 2,284 tokens to every session, about $0.0114 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