Anubis-MCP: Instructions file for GitHub Copilot

.github/copilot-instructions.md

Anubis-MCP copilot-instructions.md is an instructions file for GitHub Copilot from Hive-Academy/Anubis-MCP. It costs 4,467 tokens per session, scanned A, original, MIT.

Instructions for Anubis, a workflow protocol for coordinating AI agents during software development. It requires the agent to track its current role, task, step, and execution state.

In plain words
What is it for?
Use it when running a structured Anubis workflow, switching between assigned roles, recovering after questions, or following its MCP-based process.
Why use it?
It helps workflows survive interruptions by preserving context and resuming from the correct stage.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file.

This is Hive-Academy/Anubis-MCP's own configuration. It tells GitHub Copilot how to work on Anubis-MCP 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 Anubis-MCP configures โ†’

Reuse

Borrowing it

Nothing to install: this file belongs to Hive-Academy/Anubis-MCP. 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/Hive-Academy/Anubis-MCP/main/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/Hive-Academy/Anubis-MCP

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 Anubis-MCP copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hive-academy/anubis-mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/hive-academy/anubis-mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/hive-academy/anubis-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hive-academy/anubis-mcp/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>

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

agentmods 80ร—15 button for Anubis-MCP copilot-instructions.md

Your own site ยท 80ร—15
<a href="https://agentmods.dev/instructions/hive-academy/anubis-mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/hive-academy/anubis-mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,467 This file is loaded in full into every session.
When invoked 4,467 The same file โ€” it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file โ€” 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 $0.04467 $0.04467
Opus 5 $0.02233 $0.02233
Sonnet 5 $0.00893 $0.00893
Haiku 4.5 $0.00447 $0.00447

Measured 9d ago against content hash 467f5256bf1d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

Anubis-MCP copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories โ€” prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ€” measured 9d 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 ยท 532 lines

How it starts

The opening of the file, as written. The whole thing โ€” 532 lines โ€” stays where its author put it; the contents beside it link to each section on GitHub.

๐Ÿบ Anubis - Intelligent Guidance for AI Workflows: Universal AI Agent Protocol

You are an Expert Workflow AI Agent specialized in software development using the Anubis MCP Server. Your mission is to execute structured, quality-driven workflows through role-based collaboration and strategic delegation

Transform chaotic development into organized, quality-driven workflows

Follow these rules precisely to ensure successful workflow execution


๐Ÿ“Š WORKFLOW STATE TRACKER - MAINTAIN THIS MENTALLY

Field Value
CURRENT ROLE [update with each transition]
CURRENT ROLE ID [update with each transition]
CURRENT STEP [update with each step]
CURRENT STEP ID [update with each step]
EXECUTION ID [from bootstrap response]
TASK ID [from bootstrap or task creation]

โš ๏ธ CRITICAL: WORKFLOW INTERRUPTION PROTOCOL

When a workflow is interrupted by questions or discussions:

  1. PRESERVE STATE - Maintain current role and execution context
  2. ADDRESS QUERY - Answer the user's question or clarification
  3. RESUME PROTOCOL - Explicitly state "Resuming workflow as [current role]"
  4. NEVER SWITCH ROLES - Unless explicitly transitioning through MCP tools
  5. INCORPORATE NEW CONTEXT - Integrate new information without abandoning workflow steps

๐Ÿ›‘ INTERRUPTION RECOVERY PROCEDURE

If you detect you've broken workflow:

  1. STOP implementation immediately
  2. ACKNOWLEDGE the protocol violation clearly
  3. RESTORE your last valid role state
  4. RE-REQUEST current step guidance
  5. RESUME proper execution with correct role boundaries
// For workflow recovery, use get_active_executions then step_guidance
const activeExecutions = await workflow_execution_operations({
  operation: 'get_active_executions',
});

// Then re-request step guidance with extracted IDs
const guidance = await get_step_guidance({
  executionId: '[extracted-id]',
  roleId: '[extracted-role-id]',
});

// Explicitly acknowledge resumption
console.log('Resuming workflow as [role name] with proper boundaries');

Read the full file on GitHub ยท 532 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. 9d ago First seen ยท 532 lines ยท 4,467 tokens per session scan A 467f5256bf1d

Subscribe to this mod's changes

Anubis-MCP copilot-instructions.md is an instructions file published in the GitHub repository Hive-Academy/Anubis-MCP (124 stars, last pushed 11mo ago), licensed MIT. It adds 4,467 tokens to every session, about $0.0223 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.

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 ยท 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 ยท 5,153 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 ยท 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 ยท 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 ยท 4,469 tokens

spec-kit AGENTS.md

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

github/spec-kit ยท 7,104 tokens