Awesome-Agentic-Engineering AGENTS.md

Project-specific instructions for contributing to an open list of resources about engineering AI agents. They define how agents should read the repository guidance, review entries, and maintain the README as the main product.

In plain words
What is it for?
Use them when reviewing entries, scoring new additions, maintaining the README or appendix, or reviewing pull requests.
Why use it?
They keep contributions selective, well-supported, clearly organized, and focused on reliable engineering rather than simply adding more tools.

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/natnew/awesome-agentic-engineering/agents-md
Clone the repo
git clone --depth 1 https://github.com/natnew/Awesome-Agentic-Engineering

Made for: Codex, OpenCode.

Per session 3,488 This file is loaded in full into every session.
When invoked 3,488 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 $0.03488 $0.03488
Opus 5 $0.01744 $0.01744
Sonnet 5 $0.00698 $0.00698
Haiku 4.5 $0.00349 $0.00349

Measured 2d ago against content hash 1b91cb9812c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Awesome-Agentic-Engineering 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 · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Operating protocol for AI coding agents working in this repository.

Claude Code should read CLAUDE.md first, then use this file as the shared repository contract. Other agents should start here. Follow repository-local guidance over generic awesome-list assumptions.

Repository North Star

This is a public, maintained awesome list for agentic AI engineering. The README.md is the product: a durable, high-signal, navigable map of how to build reliable, observable, production-grade agentic systems — for readers, contributors, and AI agents.

The list is curated, not accumulated. Each entry should help a reader understand an architecture, find a credible resource, or compare related tools. Selectivity, durability, clear placement, evidence discipline, and neutral description quality matter more than volume.

Editorial stance, applied to every inclusion decision and maintainer comment: reliability over novelty · evaluation over intuition · architecture over tooling · systems thinking over prompt engineering.

Agent Role

Agents may help with:

  • README and appendix maintenance when explicitly asked
  • New entry review and rubric scoring
  • Pull request review
  • Issue triage and issue-to-entry conversion
  • Broken-link checks
  • Duplicate detection across README.md and appendix/
  • Section placement
  • Description tightening and promo-wording neutralisation
  • Evidence-tag checks
  • Maintainer comment drafts
  • Small, safe cleanup edits when explicitly requested

Agents must not:

  • Add speculative or low-signal entries
  • Inflate claims or preserve promotional wording
  • Reorganise the list or move entries between sections without explicit instruction
  • Run broad formatting sweeps
  • Edit unrelated files
  • Rewrite the maintainer's style unnecessarily
  • Turn one contribution into a broad structural change
  • Change the rubric, merge threshold, or contribution templates as part of an unrelated task
  • Touch protected or generated areas unless explicitly instructed

Read the full file on GitHub · 320 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 · 320 lines · 3,488 tokens per session scan A 1b91cb9812c4

Subscribe to this mod's changes

Awesome-Agentic-Engineering AGENTS.md is an instructions file published in the GitHub repository natnew/Awesome-Agentic-Engineering (4 stars, last pushed 8d ago), licensed MIT. It adds 3,488 tokens to every session, about $0.0174 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.

Related

Other instructions, from other repositories

Awesome-Prompt-Engineering AGENTS.md

Instructions for natnew/Awesome-Prompt-Engineering, covering agents.md, repository north star, agent role, trust boundary and read order.

natnew/Awesome-Prompt-Engineering · 2,054 tokens

Awesome-Prompt-Engineering CLAUDE.md

Instructions for natnew/Awesome-Prompt-Engineering, covering claude.md, north star, claude's role, claude behaviour rule and always-loaded context.

natnew/Awesome-Prompt-Engineering · 1,800 tokens

Awesome-Prompt-Engineering copilot-instructions.md

Instructions for natnew/Awesome-Prompt-Engineering, covering github copilot instructions, about this repository, how to treat the repository, contribution standard and reviewing suggested additions.

natnew/Awesome-Prompt-Engineering · 1,416 tokens

Awesome-Prompt-Engineering contribution-review.instructions.md

Instructions for natnew/Awesome-Prompt-Engineering, covering reviewing pull requests and issues, tone, how to respond, explaining quality concerns and maintainer judgement.

natnew/Awesome-Prompt-Engineering · 403 tokens

Awesome-Prompt-Engineering readme-curation.instructions.md

Instructions for natnew/Awesome-Prompt-Engineering, covering curating the main list (readme.md), structure and ordering, descriptions, links and before adding.

natnew/Awesome-Prompt-Engineering · 432 tokens

Awesome-Prompt-Engineering repository-maintenance.instructions.md

Instructions for natnew/Awesome-Prompt-Engineering, covering maintenance edits across markdown files, keep changes minimal, preserve voice and structure, no large or structural changes without direction and readability.

natnew/Awesome-Prompt-Engineering · 368 tokens