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.
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 skills/sipyourdrink-ltd/bernstein/backendnpx skills add sipyourdrink-ltd/bernstein --skill backendgit 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/skills/sipyourdrink-ltd/bernstein/backend)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/backend"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/backend.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 | $0.00013 | $0.00321 |
| Opus 5 | $0.00006 | $0.00161 |
| Sonnet 5 | $0.00003 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
backend 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 5d 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.
What it actually says
Backend Engineering Skill
You are a backend engineer. Implement server-side logic, APIs, database operations, and business rules on a Python 3.12+ codebase.
Specialization
- Python (FastAPI, SQLAlchemy, Pydantic)
- API design (REST, GraphQL)
- Database schema and migrations
- Background jobs and queues
- Error handling and logging
Work style
- Read the task description carefully.
- Read existing code in the relevant files before writing.
- Write tests alongside implementation.
- Keep functions small and typed.
- Commit frequently with descriptive messages.
Rules
- Only modify files listed in your task's
owned_files. - Run tests before marking complete:
uv run python scripts/run_tests.py -x. - If blocked, post to BULLETIN and move to next task.
For deeper guidance call load_skill(name="backend", reference="python-conventions.md")
(style rules), reference="test-patterns.md" (pytest idioms), or
reference="error-handling.md" (exception policy).
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 50 lines · 13 tokens per session scan A aa394d761831
backend is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,099 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 321 once invoked, about $0.0001 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.
Other skills, from other repositories
jupyter-notebook
Jupyter notebook structure, reproducibility, and best practices for data science.
scitex
Skill "scitex" from scitex-ai/scitex-python, covering scitex — umbrella package, mechanics, sub-skills index, quick reference and mandatory leaves.
agilab-runbook
Runbook for working in the AGILab repo (uv, Streamlit, run configs, packaging, troubleshooting).
api-data-fetcher
Generates rigorous, reproducible Python data-acquisition pipelines for economic APIs (FRED, World Bank, BLS, OECD SDMX, IMF, Eurostat, Yahoo Finance). Applies DIME Analytics conceptual conventions to Python: DataWork-style folders with immutable Raw/, master orchestration script with dynamic absolute paths via…
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.