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/hrithik-gavankar/brainstack/copilot-instructionsgit clone --depth 1 https://github.com/Hrithik-Gavankar/brainstackWhat 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 | $0.00679 | $0.00679 |
| Opus 5 | $0.00340 | $0.00340 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
brainstack 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brainstack Context
You are assisting [YOUR NAME], a [YOUR ROLE] at [YOUR COMPANY], with [X]+ years of industry experience.
Career Context
- Current role ([START DATE]–): [Role title] — [brief description of what you do]
- Previous role ([DATES]): [Role] — [technologies, key achievements]
- Before that ([DATES]): [Role] — [technologies, key achievements]
- Goal: [Your career goal, e.g. "Become a Staff Engineer", "Transition to ML Engineering"]
Full Skills Inventory
- Backend: [Languages, frameworks, databases you use]
- Frontend: [UI frameworks, CSS tools, design systems]
- Infrastructure: [CI/CD, cloud, containers, orchestration]
- Current focus: [What you're actively learning/building]
Workspace Layout
[Brief description of your repo structure — e.g. "Monorepo with 5 packages" or "12 microservice repos"]
Engineering Profile
- Strongest in: [Your top 3-5 technical strengths with context]
- Growing in: [Areas you're actively developing]
- Underused skills: [Skills proven elsewhere but not applied in current role]
- Work style: [Your patterns — e.g. "test-driven", "prototype-first", "documentation-heavy"]
- Peak hours: [When you do your best work]
When Helping Me
- [Instruction for the AI — e.g. "Be aware of my multi-repo context"]
- [Instruction — e.g. "Push me toward architecture ownership"]
- [Instruction — e.g. "Reference my existing test patterns when writing tests"]
- [Instruction — e.g. "Flag security implications proactively"]
- [Instruction — e.g. "Remind me to leverage underused skills"]
engineer-brain Commands
When the user asks about standups, syncs, quarterly reviews, reflections, or work patterns,
refer to .engineer-brain/COMMANDS.md for full command logic.
Available commands:
sync— generate daily standup notes from git historyupdate— refresh BRAIN.md from 30-day git scanquarterly— generate quarterly review content (90-day scan)reflect— pattern analysis and recommendationsscan [days]— raw git scan outputdoctor— brain health check and completeness scorewatch [--repos ...] [--stale-days N] [--loop N]— PR digest across workspace repos
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 First seen · 65 lines · 679 tokens per session scan A a433ca68c9a4
brainstack copilot-instructions.md is an instructions file published in the GitHub repository Hrithik-Gavankar/brainstack (5 stars, last pushed 11d ago), licensed MIT. It adds 679 tokens to every session, about $0.0034 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
agentlens CLAUDE.md
Instructions for RogerReed/agentlens, covering agentlens mcp and recurring maintenance tasks.
ctxmem AGENTS.md
Instructions for DoppiaG93/ctxmem: This repo has a ctxmem memory: a shared, git-committed record of decisions and code context. Treat it as your first source of truth and keep it correct. Follow this loop on EVERY request, without being asked.
career-copilot copilot-instructions.md
Instructions for RajjjAryan/career-copilot: Read and follow all instructions in INSTRUCTIONS.md at the repository root.
awesome-context-engine copilot-instructions.md
Copilot instructions for chefallan/awesome-context-engine, covering awesome-context-engine integration, when to fire ace commands, self-healing protocol and copilot instructions.
awesome-context-engine AGENTS.md
AGENTS.md instructions for chefallan/awesome-context-engine, covering agent rules and awesome-context-engine integration.
awesome-context-engine GEMINI.md
Gemini CLI instructions for chefallan/awesome-context-engine, a project described as: Portable repo memory for AI coding agents. Keeps context current across Copilot, Claude, Cline, Continue, and Cursor with automatic indexing, compact sync, and strict security mode.