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 rules/sipyourdrink-ltd/bernstein/architecturegit clone --depth 1 https://github.com/sipyourdrink-ltd/bernsteinWhat 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 | $0.00195 | $0.00195 |
| Opus 5 | $0.00097 | $0.00097 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
architecture 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.
What it actually says
Top-level entry points exposed by the package:
| Command | Purpose |
|---|---|
bernstein |
bernstein.cli.main:cli |
bernstein-worker |
bernstein.core.worker:main |
bernstein-bench |
bernstein.eval.bench.bench_cli:bench_group |
Back-compat aliases. Legacy import paths (e.g. bernstein.core.orchestrator) are served by a sys.meta_path finder, not by physical shim files. The mechanism lives in src/bernstein/core/__init__.py as _CoreRedirectFinder driven by the _REDIRECT_MAP dict - add new aliases there rather than creating shim modules at the old path.
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.
- 3d ago First seen · 17 lines · 195 tokens per session scan A fc27a23ce6c9
architecture is a cursor rule published in the GitHub repository sipyourdrink-ltd/bernstein (1,038 stars, last pushed 2d ago), licensed Apache-2.0. It adds 195 tokens to every session, about $0.0010 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 cursor rules, from other repositories
cursorrules
Do NOT invent repository facts. Before editing, run: npm run knowledge:context -- --task=" " and read .ai/local/current-context.md.
langchain
LangChain: chains, agents, memory, tools.
mcp-server
MCP (Model Context Protocol) server architecture and implementation.
fern-docs-generation
The custom internal Fern documentation generator automatically creates MDX documentation for Airweave connectors by introspecting Python source code using AST (Abstract Syntax Tree) parsing.
finops-enablement-lead
Builds and runs the training, documentation, champions network, and internal communication that turns individual engineers and product managers into daily FinOps practitioners. Scales the FinOps culture past the central team.
showback-chargeback-architect
Designs the model that turns shared cloud costs into team-level P&L. Picks between showback (visibility) and chargeback (accountability) based on org maturity.