agentmods.dev

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 →

not rated 2repo 2mo ago A scan 622 tokens original MIT
View source ↗ agronetlabs/ATF-AI agronet.ai
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/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ATF-AI copilot-instructions.md

Your own site · 80×15
<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="Reviewed on agentmods" width="80" 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. A grade says what 26 rules found in the file — not that it is safe.
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 5.5 $0.00249 $0.00249
Sonnet 5.5 $0.00124 $0.00124
Haiku 4.5 $0.00062 $0.00062

Measured 2mo ago against content hash 7a386960ad5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 2mo 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. 2mo 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 2mo ago), licensed MIT. It adds 622 tokens to every session, about $0.0025 per session on Opus 5.5. 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.

Autonomous Agentsai-governancecompliancefintechframeworkprotocol
Related

ATF-AI copilot-instructions.md compared with instructions from other repositories

ATF-AI copilot-instructions.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ATF-AI copilot-instructions.mdagronetlabs/ATF-AIInstructions file22mo agoMITA622GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode