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.
npx agentmods add instructions/jared13pg/ai-engineering-workflow/agents-mdgit clone --depth 1 https://github.com/Jared13PG/ai-engineering-workflowWhat 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 | $0.01404 | $0.01404 |
| Opus 5 | $0.00702 | $0.00702 |
| Sonnet 5 | $0.00281 | $0.00281 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
ai-engineering-workflow 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.
How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Identity
This repository contains a Codex Skill named:
ai-engineering-workflow
The purpose of this project is to provide a reusable AI engineering workflow for Codex. The skill helps Codex handle complex assignments, coding projects, data analysis tasks, research prototypes, and multi-file development work using a structured engineering process.
The workflow is:
issue-create → issue-breakdown → issue-execute → issue-update → issue-status → issue-close
This project should make AI-assisted development more reliable by enforcing context gathering, requirement clarification, task decomposition, atomic execution, verification, documentation updates, and final handoff.
Main Skill Location
The main skill files are located at:
.agents/skills/ai-engineering-workflow/
The core file is:
.agents/skills/ai-engineering-workflow/SKILL.md
Do not rename the skill directory unless the user explicitly asks.
Do not change the skill name unless the user explicitly asks.
The skill name must remain:
ai-engineering-workflow
Repository Structure
Expected repository structure:
ai-engineering-workflow/
├── README.md
├── AGENTS.md
├── LICENSE
├── CHANGELOG.md
├── .gitignore
├── .gitattributes
├── examples/
│ ├── homework-test-plan.md
│ └── local-validation-result.md
└── .agents/
└── skills/
└── ai-engineering-workflow/
├── SKILL.md
├── references/
│ ├── workflow-overview.md
│ ├── issue-create-guide.md
│ ├── issue-breakdown-guide.md
│ ├── issue-execute-guide.md
│ ├── issue-update-status-guide.md
│ ├── issue-close-guide.md
│ └── quality-control.md
└── assets/
└── templates/
├── issue-template.md
├── system-analysis-template.md
├── architecture-template.md
├── task-breakdown-template.md
├── status-template.md
└── close-report-template.md
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.
- 2d ago First seen · 230 lines · 1,404 tokens per session scan A 06c99fa11f1e
ai-engineering-workflow AGENTS.md is an instructions file published in the GitHub repository Jared13PG/ai-engineering-workflow (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,404 tokens to every session, about $0.0070 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.
Other instructions, from other repositories
project-os-for-codex AGENTS.md
Instructions for herry2059/project-os-for-codex, covering ai contributor rules, product truth, architecture and security, development workflow and agent integration contract.
mint AGENTS.md
Instructions for 3li7alaki/mint, covering mint: atomic completion ledger contract, one unit, one claim, state and worktrees, attempts and provenance and verification and reviews.
GameStudio-CodexKIT AGENTS.md
Instructions for hoatv2211/GameStudio-CodexKIT, covering gamestudio-codexkit operating contract, active sources of truth, primary distribution, repository-local maintenance and evidence.
dev-workflow CLAUDE.md
Instructions for andreaserradev-gbj/dev-workflow, covering claude.md, project overview, repository structure, generated in user's project (not in plugin repo) and development.
Codex-Engineering-Workflow-Pack AGENTS.md
AGENTS.md instructions for SetraTheXX/Codex-Engineering-Workflow-Pack, a project described as: Local-first engineering workflow toolkit for Codex: skills, Coordinator Mode, worktree isolation, guarded dispatch, and parallel agent workflows.
claude-code-harness CLAUDE.md
Instructions for viacheslav-tronko/claude-code-harness, covering claude.md — operational doctrine ({yourprojectname}), projectconfig — fill these placeholders before using, 0. top of mind — these four ride above everything, 1. mission and 2. p0 hard constraints — never violate.