mcp-devtools-server AGENTS.md

A project guide for an MCP DevTools server, a program that lets compatible AI agents use development tools. It documents the source folders, build commands, tests, and coding conventions.

In plain words
What is it for?
Use it when developing the server, running its TypeScript build, lint checks, Jest tests, documentation, or Docker and Makefile workflows.
Why use it?
It gives contributors the repository rules in one place, reducing mistakes when changing or checking the server.

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

Made for: Codex, OpenCode.

Per session 718 This file is loaded in full into every session.
When invoked 718 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 $0.00718 $0.00718
Opus 5 $0.00359 $0.00359
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 2d ago against content hash 032999b5dc09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-devtools-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 · 24 lines

How it starts

The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

The MCP DevTools server lives in src/, with src/index.ts wiring tool adapters found under src/tools/, shared helpers in src/utils/, plug-ins in src/plugins/, and generated prompts in src/instructions.md. Jest specs reside in src/__tests__, mirroring the runtime folder layout and using fixtures under src/__tests__/fixtures. Shared declaration files sit in types/, while examples/ holds sample MCP client wiring and docs/ powers the VitePress site. Dockerfiles and the Makefile mirror the npm scripts, so CI and local workflows stay aligned.

Build, Test, and Development Commands

  • npm run dev: launches the server via tsx with live TypeScript execution.
  • npm run build && npm start: produces dist/ with tsc (plus instruction copy) and runs the compiled server.
  • npm run lint, npm run lint:md, npm run lint:yaml, npm run lint:changelog: TypeScript lint, Markdown rules, YAML sanity checks, and CHANGELOG format validation.
  • npm test, npm run test:watch, npm run test:coverage: Jest in VM modules mode; use coverage before submitting non-trivial changes.
  • npm run docs:dev / npm run docs:build: preview or generate the VitePress documentation site.

Coding Style & Naming Conventions

TypeScript is authored in strict ESM mode with two-space indentation and trailing commas enforced by eslint.config.js. Prefer descriptive camelCase for variables/functions, PascalCase for classes, and kebab-cased filenames (e.g., file-validation-tools.ts). Re-export shared contracts through types/ instead of deep relative imports. Run npm run lint prior to commits; the configuration already includes @typescript-eslint rules for null safety, explicit return types, and import ordering.

Testing Guidelines

Tests belong next to their domain peers under src/__tests__ and should mirror folder names (tools/git-tools.test.ts exercises src/tools/git-tools.ts). Use Jest describe blocks for tool categories and prefer deterministic fixtures over shelling out. Aim to cover new code paths plus the caching utilities; add coverage assertions when extending cache or suggestion logic. Run npm test locally and npm run test:coverage before opening a PR to catch any regressions flagged by the CI thresholds.

Read the full file on GitHub · 24 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 · 24 lines · 718 tokens per session scan A 032999b5dc09

Subscribe to this mod's changes

mcp-devtools-server AGENTS.md is an instructions file published in the GitHub repository rshade/mcp-devtools-server (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 718 tokens to every session, about $0.0036 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.