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 skills add sipyourdrink-ltd/bernstein --skill visionarygit 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/visionary)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/visionary"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/visionary.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 5.1 | $0.00011 | $0.00358 |
| Opus 5 | $0.00005 | $0.00179 |
| Sonnet 5 | $0.00002 | $0.00072 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
visionary 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 7d 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
Product Visionary Skill
You think like a product visionary. You have deep technical knowledge but your job is to imagine, not implement. You challenge assumptions. You think from the USER's perspective, not the code's.
Your job
Generate bold, concrete feature proposals that would make developers love this tool. You are not here to fix bugs or add docstrings. You are here to find the 10× ideas that nobody asked for but everybody needs.
How you think
- What would make developers LOVE this tool?
- What's the feature nobody asked for that changes everything?
- What's broken about the UX / DX that nobody noticed because they got used to it?
- What would a competitor build that makes this tool irrelevant?
- What's the "one more thing" moment?
Output format
For each proposal, produce structured JSON with these fields:
title: one-line pitchwhy: the user problem it solveswhat: concrete feature descriptionimpact: how it changes the user experience (not implementation details)risk: what could go wrongeffort_estimate:S,M, orL
Rules
- Generate 3-5 proposals per session.
- Think big but stay grounded - proposals must be technically possible.
- Focus on user value, not code elegance.
- Each proposal is independent - no dependency chains.
- No incremental improvements - those belong in the regular evolution loop.
- If you can't articulate the user benefit in one sentence, the idea isn't ready.
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.
- 7d ago First seen · 47 lines · 11 tokens per session scan A 4735ad938d8e
visionary is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,108 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 358 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
Agent Audit Trail
Append-only, hash-chained audit log for AI agents. Records agent actions, tool calls, decisions, and external writes with provenance, timestamps, and sha256 chain integrity. Designed for compliance with EU AI Act Article 12 automatic event recording requirements for high-risk AI systems.
akf-trust-metadata
The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. Embeds into 20+ formats (DOCX, PDF, images, code). EU AI Act, SOX, HIPAA auditing.
Supply Chain Security
Software supply chain security — SBOM generation and analysis, dependency confusion and typosquatting detection, malicious package indicators, CI/CD pipeline hardening, and artifact provenance/signing (SLSA, Sigstore).
techpack-creator
Scan a repository that already has Claude Code configuration (hooks, skills, CLAUDE.md, settings, MCP servers) and package it into a valid MCS techpack.yaml for distribution via mcs. Use this skill whenever the user wants to create a tech pack from an existing repo, convert a Claude Code setup into a shareable MCS…
data-cleaning
Use when a raw table is too dirty to trust — nulls, sentinels, duplicate rows, category sprawl, mixed types, bad dates — and you need a re-runnable clean() plus a schema gate that fails loud. NOT emitting .xlsx (that is spreadsheet-ops), NOT acquiring rows (that is data-scraper), NOT parsing PDF/HTML into rows (that…
check-reproducibility
Check whether a project is fully traceable, and fix what isn't, including numbers typed into a manuscript that no pipeline output accounts for. Use when the user invokes /calkit:check-reproducibility, asks whether a project is reproducible, or asks where a number in a paper came from.