brain-os copilot-instructions.md

brain-os copilot-instructions.md is an instructions file for GitHub Copilot from brainOS-HQ/brain-os. It costs 606 tokens per session, scanned A, original, MIT.

A set of GitHub Copilot instructions for Brain OS, a system that stores a project's operational state in a .brain folder and exposes it through tools. It tells Copilot to follow the repository's AGENTS.md rules.

In plain words
What is it for?
Use it when Copilot works on Brain OS and needs guidance about priorities, decisions, plans, blockers, or the correct output format.
Why use it?
It keeps Copilot from answering project-state questions by searching implementation code instead of using the system's stored state. It also defines rules for formatting and handling known bugs.

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/brainos-hq/brain-os/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/brainOS-HQ/brain-os

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 brain-os copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brainos-hq/brain-os/copilot-instructions.svg)](https://agentmods.dev/instructions/brainos-hq/brain-os/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/brainos-hq/brain-os/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/brainos-hq/brain-os/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 606 This file is loaded in full into every session.
When invoked 606 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 $0.00606 $0.00606
Opus 5 $0.00303 $0.00303
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00061 $0.00061

Measured 4d ago against content hash 8993946288ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brain-os 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 4d 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 · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot instructions

This repo is Brain OS — an MCP server for persistent operational state. State lives in .brain/.

Read this first

All agent instructions for this repo live in AGENTS.md. Follow that document. This file exists only so VS Code GitHub Copilot picks up the same rules.

Critical rules (also in AGENTS.md)

  1. Use the Brain OS MCP tools as the primary data source for any question about project state, priorities, decisions, plans, blockers, or focus. The tools are exposed as brain-os in your MCP server list (entity_read, focus_get, decision_log, decision_check, decision_refresh, plan_read, plan_advance, pattern_detect, semantic_recall, etc.). Do NOT grep source code like src/tools/focus-get.ts to answer "what should I focus on" — that's the implementation of the tool, not the answer. Call the tool itself.

  2. No todo lists for state-reading questions. When the user asks "what should I work on" or "scan the project", call the MCP tool and return the answer directly. Skip the "I'll create a short todo list and then..." preamble.

  3. Format output as compact tables, not paragraphs. See "Output formatting" in AGENTS.md. For focus_get, return a fixed-column table:

    ENTITY               SCORE   MOMENTUM   NEXT
    project-alpha        75      high       Recruit 5 for usability test
    ...
    

    Then one line of do_not_do, one line of staleness_alerts. No long-form rephrasing.

  4. Mutation safety. Before any decision_log, entity_update, or plan_update, call decision_check with a short description of the proposed action. If status is conflict, do NOT proceed without explicit user confirmation.

  5. Command vocabulary. When the user types brain, focus, decide, wrap, retro, patterns, graph, or strategy in chat (with or without a leading /), run the matching MCP tool sequence from the table in AGENTS.md. Do not search the repo for these words.

  6. Terseness. Don't end every response with "would you like me to do X, Y, or Z?" — one suggested next move is enough.

Read the full file on GitHub · 33 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. 4d ago First seen · 33 lines · 606 tokens per session scan A 8993946288ba

Subscribe to this mod's changes

brain-os copilot-instructions.md is an instructions file published in the GitHub repository brainOS-HQ/brain-os (6 stars, last pushed 11d ago), licensed MIT. It adds 606 tokens to every session, about $0.0030 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.