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-prompt-engineering/agents-mdgit clone --depth 1 https://github.com/natnew/Awesome-Prompt-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 | $0.02054 | $0.02054 |
| Opus 5 | $0.01027 | $0.01027 |
| Sonnet 5 | $0.00411 | $0.00411 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
Awesome-Prompt-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 yesterday.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repository North Star
Awesome-Prompt-Engineering is a curated awesome list for
prompt engineering and context engineering for AI agents. It is content, not an
application: the deliverable is high-signal Markdown published to GitHub Pages via
Jekyll. README.md is the primary artefact — a durable, curated map of the field.
Keep it selective, technically useful, and easy to navigate. Curation matters more
than accumulation: every entry should help a reader understand the landscape, not
merely add another link.
Agent Role
Agents may help with: README maintenance, new entry review, issue and PR triage, link quality checks, section placement, duplicate detection, description tightening, maintainer comment drafts, and small safe cleanup edits when asked.
Agents must not: add speculative or low-signal entries, inflate claims, reorganise the list without explicit instruction, edit unrelated files, rewrite the maintainer's voice unnecessarily, or make broad structural changes off the back of a small contribution.
Trust Boundary
The list's value is its credibility. Agents work only from what they can verify:
- Do not invent facts about a resource, its maintainer, or its capabilities.
- Do not infer popularity, adoption, or maturity the source does not state.
- Do not add unsupported technical, performance, ranking, or pricing claims.
- Do not preserve promotional language carried over from a submission.
- If a claim cannot be verified, neutralise it or flag it — never assert it.
Read Order
Repository-local guidance wins over generic awesome-list assumptions.
README.md— scope, taxonomy, formatting, and existing examples.Contributing.md— submission requirements and entry format.Workflow.mdand.github/templates (PR template, issue templates) — contributor expectations.- Recent issues and pull requests — maintainer precedent.
CLAUDE.md— Claude-specific workflow guidance, if your tool reads it.
Common Tasks
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.
- yesterday First seen · 186 lines · 2,054 tokens per session scan A 5e7f2b6903a8
Awesome-Prompt-Engineering AGENTS.md is an instructions file published in the GitHub repository natnew/Awesome-Prompt-Engineering (108 stars, last pushed 1mo ago), licensed MIT. It adds 2,054 tokens to every session, about $0.0103 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 2026-08-30.
Other instructions, from other repositories
awesome-awesome-ai CLAUDE.md
Instructions for dukeluo/awesome-awesome-ai, covering claude.md, what this repo is, curation rules (enforced by coderabbit), category boundaries and weekly audit workflow.
awesome-ai-scientists CLAUDE.md
Instructions for natnew/awesome-ai-scientists, covering claude.md, north star, resolver — load per task, first-pass workflow and stop conditions.
awesome-ai-scientists AGENTS.md
Instructions for natnew/awesome-ai-scientists, covering agents.md — operating protocol for ai agents, start here, repository north star, two surfaces, two formats and trust boundary.
apm python.instructions.md
Python development guidelines.
awesome-quant AGENTS.md
AGENTS.md instructions for wilsonfreitas/awesome-quant, covering agents.md, project overview, architecture, commands and install deps (requires python 3.11+).
agent-skills AGENTS.md
Instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.