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.
npx agentmods add instructions/brainos-hq/brain-os/copilot-instructionsgit clone --depth 1 https://github.com/brainOS-HQ/brain-osWrote 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/brainos-hq/brain-os/copilot-instructions)<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>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 | $0.00606 | $0.00606 |
| Opus 5 | $0.00303 | $0.00303 |
| Sonnet 5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
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.
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)
-
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-osin 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 likesrc/tools/focus-get.tsto answer "what should I focus on" — that's the implementation of the tool, not the answer. Call the tool itself. -
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.
-
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 ofstaleness_alerts. No long-form rephrasing. -
Mutation safety. Before any
decision_log,entity_update, orplan_update, calldecision_checkwith a short description of the proposed action. If status isconflict, do NOT proceed without explicit user confirmation. -
Command vocabulary. When the user types
brain,focus,decide,wrap,retro,patterns,graph, orstrategyin 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. -
Terseness. Don't end every response with "would you like me to do X, Y, or Z?" — one suggested next move is enough.
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.
- 4d ago First seen · 33 lines · 606 tokens per session scan A 8993946288ba
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.
Other instructions, from other repositories
turbo_quant_memory AGENTS.md
AGENTS.md instructions for Lexus2016/turbo_quant_memory, covering agents.md, project identity, memory usage policy, session continuity (start-of-session and compaction) and accessing project secrets (phase 9).
turbo_quant_memory CLAUDE.md
Claude Code instructions for Lexus2016/turbo_quant_memory, covering claude.md, tqmemory workflow, practical rule and secrets vault (phase 9).
personal-model AGENTS.md
Instructions for Intuition-Lab/personal-model, covering agents.md, runtime boundary, commands, pipeline and documentation map.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
memex AGENTS.md
Instructions for iamtouchskyer/memex, covering memex — agent working instructions, what is this, before you touch anything, how the code is layered and files you'll actually need.