ai-engineering-workspace: Instructions file for Codex

AGENTS.md

ai-engineering-workspace AGENTS.md is an instructions file for Codex, OpenCode from yuri-semenenko/ai-engineering-workspace. It costs 2,302 tokens per session, scanned B, original, MIT.

Repository instructions for AI coding assistants working in the ai-engineering-workspace project. They explain which instruction files control the assistant, how the files are organised, and where repository rules belong.

In plain words
What is it for?
Use them when changing agent instructions, adding skills, or deciding where a rule or piece of project guidance should be stored.
Why use it?
They reduce conflicting or duplicated guidance across different coding tools. They help an assistant apply the right project rules without treating every document as an independent source of truth.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is yuri-semenenko/ai-engineering-workspace's own configuration. It tells Codex and OpenCode how to work on ai-engineering-workspace 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 ai-engineering-workspace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yuri-semenenko/ai-engineering-workspace. 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/yuri-semenenko/ai-engineering-workspace/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/yuri-semenenko/ai-engineering-workspace

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 ai-engineering-workspace AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yuri-semenenko/ai-engineering-workspace/agents-md.svg)](https://agentmods.dev/instructions/yuri-semenenko/ai-engineering-workspace/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yuri-semenenko/ai-engineering-workspace/agents-md"><img src="https://agentmods.dev/badge/instructions/yuri-semenenko/ai-engineering-workspace/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,302 This file is loaded in full into every session.
When invoked 2,302 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.02302 $0.02302
Opus 5 $0.01151 $0.01151
Sonnet 5 $0.00460 $0.00460
Haiku 4.5 $0.00230 $0.00230

Measured 3d ago against content hash dcaacd53533c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

ai-engineering-workspace AGENTS.md scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`persona/copilot-instructions.md`, `claude-code/.claude/settings.json` —
AGENTS.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Repository contract for ai-engineering-workspace, and tool-agnostic: Codex and Gemini CLI read it directly, Copilot CLI and VS Code read it as agent instructions, and root CLAUDE.md imports it for Claude Code. It is a router — what is specific to this repository, plus a link to the document explaining each rule. It does not restate the README, the persona, the methodology, or the skill catalog.

Purpose

A portable methodology layer for using AI to do software engineering, shipped to four assistants: Claude Code, Codex, GitHub Copilot, and Gemini CLI.

Instruction layers

Six layers reach an assistant from here. Put a change in the layer that owns it.

Layer Owner Loading model
Persona persona/*.template.md generated by the wizard, installed per tool
Methodology docs/principles/ prose, read on demand
Repository contract that repository's root AGENTS.md always-on repository context
Skills each tool's skills/commands/prompts directory task-triggered
Adapters claude-code/, codex/, copilot/, gemini/ tool-native delivery by the installers
Guardrails settings.example.json, scripts/, scripts/hooks/, CI mechanically enforced

Persona and methodology are global and shared. A repository contract is neither: never copy persona, methodology, or a whole skill into one.

Six files share two filenames

Tool discovery dictates both names, so none of these can be renamed. Always say which one you mean by its path.

Path Scope
AGENTS.md (root) this repository's contract — the file you are reading
codex/AGENTS.md personal and global; installed to $CODEX_HOME/AGENTS.md
copilot/workspace-template/AGENTS.md a template for another repository; not in force here
CLAUDE.md (root) this repository's Claude Code adapter: the active @AGENTS.md import plus any Claude-only delta
copilot/workspace-template/CLAUDE.md the @AGENTS.md adapter shipped with that template; not in force here
persona/CLAUDE.md the developer's generated persona, gitignored, installed to ~/.claude/CLAUDE.md

Read the full file on GitHub · 166 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. 3d ago First seen · 166 lines · 2,302 tokens per session scan B dcaacd53533c

Subscribe to this mod's changes

ai-engineering-workspace AGENTS.md is an instructions file published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 7d ago), licensed MIT. It adds 2,302 tokens to every session, about $0.0115 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens