ATF-AI: Instructions file for GitHub Copilot

.github/copilot-instructions.md

ATF-AI copilot-instructions.md is an instructions file for GitHub Copilot from agronetlabs/ATF-AI. It costs 622 tokens per session, scanned A, original, MIT.

Repository instructions for the ATF-AI project, covering governance, infrastructure-neutral design, adapters, and sensitive real-world-asset operations.

In plain words
What is it for?
Use them when changing ATF-AI specifications or code to follow the project’s governance files, compatibility and maturity rules, and authorization requirements.
Why use it?
They set boundaries for AI-assisted changes, clarify what belongs in the core protocol versus adapters, and require human oversight for privileged actions.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is agronetlabs/ATF-AI's own configuration. It tells GitHub Copilot how to work on ATF-AI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ATF-AI configures →

Reuse

Borrowing it

Nothing to install: this file belongs to agronetlabs/ATF-AI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agronetlabs/ATF-AI/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/agronetlabs/ATF-AI

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 ATF-AI copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/agronetlabs/atf-ai/copilot-instructions.svg)](https://agentmods.dev/instructions/agronetlabs/atf-ai/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/agronetlabs/atf-ai/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/agronetlabs/atf-ai/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 622 This file is loaded in full into every session.
When invoked 622 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 5.1 $0.00622 $0.00622
Opus 5 $0.00311 $0.00311
Sonnet 5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 6d ago against content hash 7a386960ad5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ATF-AI 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 6d 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ATF-AI Repository Instructions for GitHub Copilot

ATF-AI is an infrastructure-agnostic trust and governance protocol coordinated by AgroNet Labs LLC.

Governance Boundary

  • Treat the repository as human-governed and AI-assisted.
  • Do not describe AI-generated changes as approved, certified, or authoritative unless an authorized human maintainer has explicitly accepted them.
  • Do not self-approve or self-merge material protocol changes.
  • CI success is validation evidence, not protocol approval.
  • Follow GOVERNANCE.md, CONTRIBUTING.md, SECURITY.md, and .github/CODEOWNERS.

Core vs. Adapter Changes

  • Keep specs/atf-core-v1.md infrastructure-agnostic.
  • Put blockchain-, RWA-, cloud-, IoT-, or other domain-specific behavior in adapters unless it is genuinely universal.
  • Adapters must declare parent core compatibility and maturity (DRAFT, REVIEW, STABLE, or DEPRECATED).
  • Do not represent a DRAFT adapter as stable solely because reference code or CI exists.

RWA Privileged Actions

For admin, redemption, signer, oracle, compliance, upgrade, mint/burn, or settlement operations:

  • preserve separation between governance authorization and cryptographic execution;
  • never treat possession of a private key, signer credential, MPC share, or HSM capability as sufficient governance authority by itself;
  • preserve quorum, distinct approvers, role separation, timelocks, provenance, compliance evidence, and transaction-intent binding where the applicable policy requires them;
  • record deterministic rejection/escalation outcomes;
  • maintain rollback or compensating-control paths when atomic execution is impossible.

Reference: specs/adapters/rwa-privileged-governance.md.

Security

Never introduce production:

  • private keys;
  • seed phrases;
  • wallet recovery material;
  • MPC shares;
  • HSM secrets;
  • API secrets or bearer tokens;
  • production signing credentials.

Use clearly non-production fixtures in tests and examples.

Validation

Read the full file on GitHub · 69 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. 6d ago First seen · 69 lines · 622 tokens per session scan A 7a386960ad5e

Subscribe to this mod's changes

ATF-AI copilot-instructions.md is an instructions file published in the GitHub repository agronetlabs/ATF-AI (2 stars, last pushed 14d ago), licensed MIT. It adds 622 tokens to every session, about $0.0031 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens