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/natnew/awesome-agentic-engineering/agents-mdgit clone --depth 1 https://github.com/natnew/Awesome-Agentic-EngineeringWhat 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 | $0.03488 | $0.03488 |
| Opus 5 | $0.01744 | $0.01744 |
| Sonnet 5 | $0.00698 | $0.00698 |
| Haiku 4.5 | $0.00349 | $0.00349 |
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.
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.mdandappendix/ - 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
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 · 320 lines · 3,488 tokens per session scan A 1b91cb9812c4
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.
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.
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.
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.
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.
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.
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.