EngiMCP: Instructions file for Codex

AGENTS.md

EngiMCP AGENTS.md is an instructions file for Codex, OpenCode from GreenLordUA/EngiMCP. It costs 486 tokens per session, scanned A, original, MIT.

Project instructions for EngiMCP, an MCP server that manages engineering projects stored in Markdown files and Git. They define how agents should read requirements, document decisions, and make code changes.

In plain words
What is it for?
Use them when changing EngiMCP code, adding tools or data entities, updating requirements, or modifying its filesystem and project-management behavior.
Why use it?
They keep the project’s documentation, code, tests, and tool interfaces aligned while protecting project files and recorded decisions.

Instructions file for CodexOpenCode

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

This is GreenLordUA/EngiMCP's own configuration. It tells Codex and OpenCode how to work on EngiMCP 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 EngiMCP configures →

Reuse

Borrowing it

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

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 EngiMCP AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/greenlordua/engimcp/agents-md"><img src="https://agentmods.dev/badge/instructions/greenlordua/engimcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 486 This file is loaded in full into every session.
When invoked 486 The same file — it is already loaded in full.
Security scan A 0 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 $0.00486 $0.00486
Opus 5.5 $0.00194 $0.00194
Sonnet 5.5 $0.00097 $0.00097
Haiku 4.5 $0.00049 $0.00049

Measured 2mo ago against content hash 082a4a82c0fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

EngiMCP 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 2mo 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions for Codex/LLM Agents in the EngiMCP Project

General Working Mode

You are working on EngiMCP: an MCP server for managing engineering projects in Markdown/Git.

Core principle: documentation is the source of truth. Code must match requirements, tests must match requirements, and every meaningful decision must have an ADR/EDR record.

Before Changing Code

  1. Read README.md.
  2. Read docs/02_requirements/technical_requirements.md.
  3. For the specific task, read the relevant documents in docs/03_architecture, docs/04_data_model, and docs/05_mcp_interface.
  4. Do not rewrite whole documents when a focused edit is enough.

Change Rules

  • Do not remove requirements without creating an ADR/EDR.
  • Do not change a public tool contract without updating tools_spec.md and tests.
  • Every new tool must have:
    • purpose;
    • input schema;
    • output schema;
    • errors;
    • acceptance criteria.
  • Every new entity must be described in entities_and_schema.md.
  • Every write function must be atomic and safe.
  • Filesystem tools (engi_fs_*) must stay root-jailed to project_root, reject symlink escape, respect deny patterns, enforce read-only mode, and write audit logs for write/move/copy/delete/mkdir.
  • Use engi_doc_* semantics for managed engineering documents and engi_fs_* semantics only for ordinary file/folder operations.

Style

  • Documents are in English.
  • Code, file names, tool names, and schemas are in English.
  • Requirement IDs: FR-001, NFR-001, SEC-001, AC-001.
  • Decision IDs: EDR-0001, EDR-0002.
  • Task IDs: TASK-0001.

Before Finishing a Task

Check:

- whether requirements/documents were updated;
- whether any broken links appeared;
- whether the tools contract changed without tests;
- whether there is a decision-log entry for any meaningful decision;
- whether builds and type checks pass after any code change;
- whether the existing test suite passes after large changes or when explicitly requested;
- whether the change can be described in one changelog line.

Read the full file on GitHub · 52 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. 2mo ago First seen · 52 lines · 486 tokens per session scan A 082a4a82c0fe

Subscribe to this mod's changes

EngiMCP AGENTS.md is an instructions file published in the GitHub repository GreenLordUA/EngiMCP (0 stars, last pushed 4mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0019 per session on Opus 5.5. 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.

Related

EngiMCP AGENTS.md compared with instructions from other repositories

EngiMCP AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
EngiMCP AGENTS.mdGreenLordUA/EngiMCPInstructions file04mo agoMITA486Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot