Bernstein is an open-source governance layer for AI agents that applies written policies, schedules agent work deterministically, controls approvals, and records verifiable execution history. It is used to coordinate CLI coding agents and other agent workloads, including parallel runs and offline review, while the catalogue entries provide its agent workflows and controls.
Borrowing it
Nothing to install: this file belongs to sipyourdrink-ltd/bernstein. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sipyourdrink-ltd/bernstein/main/.github/copilot-instructions.mdgit clone --depth 1 https://github.com/sipyourdrink-ltd/bernsteinWrote 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/sipyourdrink-ltd/bernstein/copilot-instructions)<a href="https://agentmods.dev/instructions/sipyourdrink-ltd/bernstein/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sipyourdrink-ltd/bernstein/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/sipyourdrink-ltd/bernstein/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/sipyourdrink-ltd/bernstein/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 | $0.00740 | $0.00740 |
| Opus 5.5 | $0.00296 | $0.00296 |
| Sonnet 5.5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
bernstein 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 1mo 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions
Bernstein is the open-source governance layer for AI agents (Python 3.12+), one git worktree per task. There is no model in the coordination loop - the orchestrator is deterministic Python, NOT an LLM - so the same plan replays to a byte-identical task graph.
Architecture
src/bernstein/
core/ # 21 sub-packages (orchestration, agents, tasks, quality, ...)
__init__.py # MetaPathFinder redirects old imports to sub-packages
defaults.py # All configurable constants (150+)
server.py # FastAPI task server (HTTP :8052)
orchestration/ # Run loop, ticks, drain, scheduling
agents/ # Lifecycle, spawning, identity, signals
tasks/ # Lifecycle, store, claim, retry, models
quality/ # Gates, testing, review, architecture
security/ # Auth, RBAC, permissions, compliance
observability/ # Metrics, tracing, logging, alerting
protocols/ # MCP, A2A, ACP, gRPC, cluster
routing/ # Model routing, policies, bandit
cost/ # Tracking, budgets, forecasting
tokens/ # Monitoring, context, compaction
config/ # Seed parsing, settings, feature gates
git/ # Operations, worktrees, merge
persistence/ # Store backends, WAL, checkpoints
planning/ # Plans, recipes, planner
communication/ # Bulletin, notifications, signals
knowledge/ # Knowledge base, RAG, memory
plugins_core/ # Plugin management, skills
adapters/ # CLI agent adapters (claude, codex, gemini, etc.)
cli/ # CLI commands (commands/, display/, utils/, plan/)
tui/ # Textual TUI widgets
Key constraints
- The orchestrator/scheduler is deterministic Python. NEVER add LLM calls for coordination.
- Agents are short-lived: spawn per task, execute, exit. No long-running sessions.
- All runtime state lives in
.sdd/as files (JSONL, YAML). No databases. - Use frozen dataclasses/TypedDict for all data - never raw dicts.
- Type hints on ALL public functions. Pyright strict mode must pass.
- Async for IO-bound, sync for CPU-bound.
- New constants go in
core/defaults.py, not inline. - New modules go in the appropriate sub-package, not in
core/root.
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.
- 1mo ago Changed 58e52cdc3d9e
- 1mo ago First seen · 70 lines · 740 tokens per session scan A 9c9ee5123513
bernstein copilot-instructions.md is an instructions file published in the GitHub repository sipyourdrink-ltd/bernstein (1,330 stars, last pushed today), licensed Apache-2.0. It adds 740 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.
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.
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).