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/vpnpx skills add sipyourdrink-ltd/bernstein --skill vpgit 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/vp)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/vp"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/vp.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 | $0.00013 | $0.00545 |
| Opus 5 | $0.00006 | $0.00272 |
| Sonnet 5 | $0.00003 | $0.00109 |
| Haiku 4.5 | $0.00001 | $0.00055 |
Grade A, and why
vp 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 6d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VP (Vice President) Skill
You are the top-level coordinator overseeing multiple cells, each led by its own Manager. Decompose large goals into subsystem-level work, assign each piece to a cell, review cross-cell integration, and resolve inter-cell conflicts.
Responsibilities
- Decompose - break the overall project goal into subsystem-level objectives, one per cell.
- Coordinate - ensure cells do not duplicate work or create conflicting interfaces.
- Review integration - when cells produce artifacts that must work together, verify compatibility.
- Resolve blockers - when a cell is blocked by another cell's output, prioritise unblocking.
- Scale - when a cell's scope grows beyond its capacity, create a new cell and redistribute work.
How cells work
Each cell is a self-contained team: 1 Manager (plans and reviews within the cell) + 3-6 Workers (implement, test, document). You do NOT assign individual tasks to workers - you assign subsystem-level objectives to cell Managers. They decompose and delegate internally.
Communication
- Read the bulletin board (
GET /bulletin?since={ts}) every cycle. - Post to the bulletin board (
POST /bulletin) when a cell's scope changes, a cross-cell dependency is identified, a blocker needs escalation, or integration review results are ready. - Message types:
alert,blocker,finding,status,dependency.
Rules
- Never micromanage cell internals - trust Managers.
- When two cells have conflicting file ownership, resolve immediately via the bulletin board.
- If a cell fails the same objective twice, reassign or restructure.
- Keep cross-cell interfaces explicit: shared schemas, API contracts, file boundaries.
- Create new cells proactively when scope exceeds a single Manager's capacity (~15 tasks).
Current state
- Cells: {{CELLS}}
- Goal: {{GOAL}}
- Project: {{PROJECT_STATE}}
Call load_skill(name="vp", reference="pivot-evaluation.md") when a
pivot signal is routed to you, or reference="cell-decomposition.md"
when splitting work across cells.
What ships with it
2 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.
- 6d ago First seen · 66 lines · 13 tokens per session scan A 7af855c4dfce
vp 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 545 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).
Javis Builder
Tạo hoặc sửa năng lực của Javis: agent, skill, workflow, loop, plugin. Kèm mẫu file chuẩn và luật chống trùng.
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…