project-brain copilot-instructions.md

A set of instructions for GitHub Copilot Chat working in the Ethan-YS/project-brain repository. It explains which project context files to read, how to handle one or several workstreams, and when changes to those files need approval.

In plain words
What is it for?
Use it to start a session with the right project context, identify the active workstream, report progress and blockers, and propose updates to the repository's brain files.
Why use it?
It prevents the assistant from guessing the current project state or silently changing shared project records.

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/ethan-ys/project-brain/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Ethan-YS/project-brain

Made for: GitHub Copilot.

Per session 480 This file is loaded in full into every session.
When invoked 480 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 $0.00480 $0.00480
Opus 5 $0.00240 $0.00240
Sonnet 5 $0.00096 $0.00096
Haiku 4.5 $0.00048 $0.00048

Measured 3d ago against content hash 1233dfe452a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-brain 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 3d 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.

templates/.github/copilot-instructions.md · 49 lines

What it actually says

[Project Name] — Copilot Chat Instructions

This file is auto-loaded by GitHub Copilot Chat when working in this repo. It tells Copilot how to pick up the project's persistent context.

On session start

Decide single- or multi-workstream (look at file naming under brain/):

  • Only STATUS.md / HANDOFF.md → single-workstream
  • Multiple STATUS_<workstream>.md → multi-workstream (v2.1)

Single-workstream

Read these in order:

  1. brain/MAP.md — project map (modules, doc index, run instructions)
  2. brain/STATUS.md — current state (where we stopped, next step, blockers)
  3. brain/HANDOFF.md if it exists — previous session's still-warm thoughts

Then report briefly: project recognized + current progress + last blocker.

Multi-workstream

First read shared files: brain/MAP.md + brain/PROJECT.md. Don't guess this window's workstream — ask the user which one. Then read the corresponding STATUS_<workstream>.md + HANDOFF_<workstream>.md.

Update behavior

Don't silently modify any file in brain/. When something should be updated:

  1. Propose to the user (with reasoning)
  2. Wait for approval
  3. Then write

Specific triggers:

  • User says "update the project brain" → propose a list with reasons (what to update + why); user picks
  • A decision feels just made → ask "does this count as decided?" — don't assert
  • User signals end-of-session ("that's it / heading out") → draft brain/STATUS.md for review
  • User signals window-switch → write brain/HANDOFF.md, archive the previous one to brain/handoffs/YYYY-MM-DD-HHMM.md

Multi-workstream (v2.1): scope STATUS / HANDOFF / handoffs to the current workstream. PROJECT / MAP / DECISIONS / topics are shared.

Project red lines

⚠️ TODO ⚠️ — fill in red lines, or confirm "no explicit red lines for this project"

Reference

Full methodology: https://github.com/Ethan-YS/project-brain/blob/main/METHODOLOGY.md

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. 3d ago First seen · 49 lines · 480 tokens per session scan A 1233dfe452a4

Subscribe to this mod's changes

project-brain copilot-instructions.md is an instructions file published in the GitHub repository Ethan-YS/project-brain (170 stars, last pushed 2mo ago), licensed MIT. It adds 480 tokens to every session, about $0.0024 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

claude-code-ultimate-guide AGENTS.md

AGENTS.md instructions for FlorianBruniaux/claude-code-ultimate-guide, covering claude code ultimate guide - project context, purpose, repository structure, published at: https://cc.bruniaux.com/whitepapers/ and key files.

FlorianBruniaux/claude-code-ultimate-guide · 2,921 tokens

claude-code-ultimate-guide CLAUDE.md

Claude Code instructions for FlorianBruniaux/claude-code-ultimate-guide, covering claude code ultimate guide - project context, purpose, repository structure, published at: https://cc.bruniaux.com/whitepapers/ and key files.

FlorianBruniaux/claude-code-ultimate-guide · 2,921 tokens

claude-code-ultimate-guide copilot-instructions.md

Copilot instructions for FlorianBruniaux/claude-code-ultimate-guide: Use /CLAUDE.md as the single source of truth for this repository.

FlorianBruniaux/claude-code-ultimate-guide · 69 tokens

muse CLAUDE.md

Instructions for myths-labs/muse, covering 🏛 constitution — muse, iron rules, skill-driven execution, context health pre-check and safety protocols.

myths-labs/muse · 2,028 tokens

Iron-mem CLAUDE.md

Instructions for BMC-INC/Iron-mem, a project described as: Agent-native memory infrastructure for AI coding assistants. Governed session capture, LLM compression, hybrid retrieval (FTS + vector + RRF), temporal knowledge graph, content-addressed storage, compliance-grade classification. Single Rust binary, MCP server.…

BMC-INC/Iron-mem · 9 tokens

muse AGENTS.md

Instructions for myths-labs/muse, covering agents.md, core constitution, 🏛 constitution — muse, iron rules and skill-driven execution.

myths-labs/muse · 29,476 tokens