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.
curl -O https://raw.githubusercontent.com/Hive-Academy/Anubis-MCP/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/Hive-Academy/Anubis-MCPWrote 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.
[](https://agentmods.dev/instructions/hive-academy/anubis-mcp/copilot-instructions)<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 80ร15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04467 | $0.04467 |
| Opus 5.5 | $0.01787 | $0.01787 |
| Sonnet 5.5 | $0.00893 | $0.00893 |
| Haiku 4.5 | $0.00447 | $0.00447 |
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 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.
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.
๐บ 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
๐ 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] |
โ ๏ธ CRITICAL: WORKFLOW INTERRUPTION PROTOCOL
When a workflow is interrupted by questions or discussions:
- PRESERVE STATE - Maintain current role and execution context
- ADDRESS QUERY - Answer the user's question or clarification
- RESUME PROTOCOL - Explicitly state "Resuming workflow as [current role]"
- NEVER SWITCH ROLES - Unless explicitly transitioning through MCP tools
- INCORPORATE NEW CONTEXT - Integrate new information without abandoning workflow steps
๐ INTERRUPTION RECOVERY PROCEDURE
If you detect you've broken workflow:
- STOP implementation immediately
- ACKNOWLEDGE the protocol violation clearly
- RESTORE your last valid role state
- RE-REQUEST current step guidance
- 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');
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.
- 2mo ago First seen ยท 532 lines ยท 4,467 tokens per session scan A 467f5256bf1d
Anubis-MCP copilot-instructions.md is an instructions file published in the GitHub repository Hive-Academy/Anubis-MCP (125 stars, last pushed 1y ago), licensed MIT. It adds 4,467 tokens to every session, about $0.0179 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 2026-08-30.
Anubis-MCP copilot-instructions.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Anubis-MCP copilot-instructions.mdHive-Academy/Anubis-MCP | Instructions file | 125 | 1y ago | MIT | A | 4,467 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |