Awesome-Agentic-Engineering copilot-instructions.md

Awesome-Agentic-Engineering copilot-instructions.md is an instructions file for GitHub Copilot from natnew/Awesome-Agentic-Engineering. It costs 907 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining a curated Markdown list about reliable, observable agent-based AI systems. They explain how to review entries, contributions, sources, links, and formatting.

In plain words
What is it for?
Use them when reviewing pull requests, adding or removing catalogue entries, checking sources, or preserving the structure and tone of the repository.
Why use it?
They help contributors judge additions consistently and avoid treating a documentation repository like application code. They also clarify which files define the project’s standards.

Instructions file for GitHub Copilot

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/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/natnew/Awesome-Agentic-Engineering

Made for: GitHub Copilot.

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 Awesome-Agentic-Engineering copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/natnew/awesome-agentic-engineering/copilot-instructions.svg)](https://agentmods.dev/instructions/natnew/awesome-agentic-engineering/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/natnew/awesome-agentic-engineering/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/natnew/awesome-agentic-engineering/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 907 This file is loaded in full into every session.
When invoked 907 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 $0.00907 $0.00907
Opus 5 $0.00453 $0.00453
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00091 $0.00091

Measured 3d ago against content hash 5a857d1257ef, 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 copilot-instructions.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 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.

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.

.github/copilot-instructions.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions

What this repository is

Awesome Agentic Engineering is a curated list about building reliable, observable, production-grade agentic AI systems. It is a maintained public resource, not an application codebase. Almost all work is Markdown curation: reviewing pull requests, assessing proposed entries, checking sources, preserving the structure and tone of README.md, and keeping links and formatting consistent.

The editorial stance is: reliability over novelty, evaluation over intuition, architecture over tooling. Apply this lens to every inclusion decision and every review comment.

How to treat this repository

  • Treat changes as curation, not engineering. There is no application to build or run.
  • The canonical content lives in README.md, with overflow and fast-moving lists under appendix/.
  • The curation contract is defined in CONTRIBUTING.md, RUBRIC.md, and ANTI-PATTERNS.md. Read these before judging any entry.
  • Match the formatting of surrounding content exactly — column order, bullet templates, emoji, and casing.

Contribution standard

Every entry is scored against the seven-dimension rubric in RUBRIC.md (each 0–3): Reliability ×3, Evidence ×3, Agentic relevance ×3, Uniqueness ×2, Maturity ×2, Licensing ×1, Community signal ×1.

  • Merge requires a weighted total of ≥ 27 / 45.
  • Hard gates: any 0 on Reliability, Evidence, or Agentic relevance blocks merge.
  • Community signal (stars, adoption) is a tiebreaker only — never sufficient on its own.

Belongs: agent architectures, orchestration, memory, evaluation, protocols and standards, tool use, multi-agent systems, and agent authority, identity, permissions, auditability, and production operations — with engineering substance and real-world signal.

Does not belong: generic LLM wrappers with no agentic primitives, vendor marketing or launch posts, unverified or launch-day benchmarks, duplicates that add no new structure or judgement, archived or single-author prototypes framed as production, stars-as-evidence, and out-of-scope tooling (chat UIs, prompt-only utilities). See ANTI-PATTERNS.md.

Read the full file on GitHub · 55 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 · 55 lines · 907 tokens per session scan A 5a857d1257ef

Subscribe to this mod's changes

Awesome-Agentic-Engineering copilot-instructions.md is an instructions file published in the GitHub repository natnew/Awesome-Agentic-Engineering (4 stars, last pushed 9d ago), licensed MIT. It adds 907 tokens to every session, about $0.0045 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