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.
git clone --depth 1 https://github.com/Ethan-YS/project-brainWrote 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/ethan-ys/project-brain/copilot-instructions)<a href="https://agentmods.dev/instructions/ethan-ys/project-brain/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ethan-ys/project-brain/copilot-instructions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 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/ethan-ys/project-brain/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ethan-ys/project-brain/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 | $0.00742 | $0.00742 |
| Opus 5.5 | $0.00297 | $0.00297 |
| Sonnet 5.5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
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 yesterday.
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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[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:
brain/MAP.md— project map (modules, doc index, run instructions)brain/STATUS.md— current state (where we stopped, next step, blockers)brain/HANDOFF.mdif it exists — last shift's report
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 — use explicit signals only (the window is named for a workstream, e.g. web-6, or the user said so); otherwise ask the user which one.
Then read the corresponding STATUS_<workstream>.md + HANDOFF_<workstream>.md.
Concurrent windows (v2.8 — MAP §6 has a "Who's on it now" roster): also check other workstreams' STATUS for requests to yours still marked sent. Once the user confirms and work begins, write this window's name + date into your workstream's roster row.
Update behavior
brain/ is written for the next session, not for the user (METHODOLOGY §4.1, v2.9.1):
STATUS/HANDOFF/MAPregistrations /RUNBOOKappends → write when the work lands, don't ask, don't report; the commit message is the recordDECISIONS/PROJECT→ write what the user said plainly; ask "does this count as decided?" only when you can't tell
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") → overwrite
brain/STATUS.md - User signals window-switch / hand off → move what's still valid out of the old
brain/HANDOFF.md(waits → STATUS, procedures and traps →brain/topics/operations/RUNBOOK.md), archive it tobrain/handoffs/YYYY-MM-DD-HHMM.md, write the new one as a shift report (six sections)
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.
- yesterday Changed · +51 tokens per session d8de0eee2ab4
- 14d ago Changed · +2 lines · +211 tokens per session 12be322cb085
- 1mo ago First seen · 49 lines · 480 tokens per session scan A 1233dfe452a4
project-brain copilot-instructions.md is an instructions file published in the GitHub repository Ethan-YS/project-brain (173 stars, last pushed yesterday), licensed MIT. It adds 742 tokens to every session, about $0.0030 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.