What is qe-mcp AGENTS.md?

Project instructions for qe-mcp, a Node.js server and command-line tool that provides a local library of quality-engineering guidance to AI clients. Quality engineering covers testing and other practices used to check software reliability.

Use it when working on qe-mcp to run its checks and self-tests, launch its command-line tools or MCP server, and follow its repository and permission rules.

It explains how to build, run, test, and structure the repository while keeping it separate from the related qe-framework project.

qe-mcp AGENTS.md — Instructions file for Codex and OpenCode by inho-team: Project instructions for qe-mcp, a Node.js server and command-line

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/inho-team/qe-mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/inho-team/qe-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/inho-team/qe-mcp/agents-md.svg)](https://agentmods.dev/instructions/inho-team/qe-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/inho-team/qe-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/inho-team/qe-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 426 This file is loaded in full into every session.

When invoked 426 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.

Model	Per session	Once invoked
Fable 5	$0.00426	$0.00426
Opus 5	$0.00213	$0.00213
Sonnet 5	$0.00085	$0.00085
Haiku 4.5	$0.00043	$0.00043

Measured 4d ago against content hash 1cb6b475c4a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qe-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 4d 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 · 49 lines

What it actually says

QE MCP

Project Overview

Name: @inho-team/qe-mcp
Description: Standalone QE expert-library MCP server and CLI sync tooling for Claude, Codex, and Gemini clients.

Tech Stack

Runtime: Node.js
Language: JavaScript ES modules (.mjs)
Protocol surface: stdio MCP server
Data corpus: local Markdown/JSON expert library under expert-library/

Build & Run

npm run check
npm run selftest
npm run runner:smoke
node scripts/qe_mcp.mjs --help
node scripts/qe_mcp_server.mjs

Project Structure

qe-mcp/
├── scripts/          # CLI, MCP server, tests, and implementation libraries
├── expert-library/   # local expert corpus, indexes, packs, skills, references
├── .qe/              # QE framework state and analysis
├── package.json
└── README.md

Constraints

Treat this repository as independent from qe-framework; do not copy qe-mcp assets back into qe-framework package payloads.
Prefer running commands from this repo root, not the workspace wrapper.
Active runner tools launch local CLIs only through bounded policy surfaces.
Do not widen runner permissions, inherited MCP config, output caps, or recursion behavior without explicit design review.
Follow existing ES module style and keep shell execution paths bounded and non-destructive by default.
See QE_CONVENTIONS.md for QE workflow rules, task status, and completion criteria.

QE Toolkit

Planning: Qplan
Spec generation: Qgs
Execution: Qatomic-run
Verification: Qcode-run-task
Project state: .qe/TASK_LOG.md

Task Log

작업 이력 및 상태: .qe/TASK_LOG.md 참조

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.

4d ago First seen · 49 lines · 426 tokens per session scan A 1cb6b475c4a1

Subscribe to this mod's changes

qe-mcp AGENTS.md is an instructions file published in the GitHub repository inho-team/qe-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 426 tokens to every session, about $0.0021 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 2026-09-01.

Testing

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

qe-mcp AGENTS.md