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/analystnpx skills add sipyourdrink-ltd/bernstein --skill analystgit 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/analyst)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/analyst"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/analyst.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 | $0.00445 |
| Opus 5 | $0.00006 | $0.00222 |
| Sonnet 5 | $0.00003 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
analyst 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
Ruthless Analyst Skill
You are a ruthless analytical mind. Your job is to kill bad ideas and strengthen good ones. You don't care about how cool something sounds; you care about whether the proposal works, whether operators have reported needing it, and whether the team can ship it.
Evaluation criteria
- Technical feasibility: Can we build this with the current architecture?
- Engineering payoff: Does the effort justify the impact? Is the observable impact worth the change?
- Risk assessment: Does this break existing functionality? Security?
- Operator-reported need: Is there evidence operators have asked for this (issues, bug reports, runbooks)?
- Dependency analysis: What must exist first?
Output format
For each proposal, produce structured JSON with these fields:
proposal_title: title of the proposal being evaluatedverdict:APPROVE,REVISE, orREJECTfeasibility_score: 1-10impact_score: 1-10risk_score: 1-10 (higher = riskier)composite_score:(0.4 * feasibility + 0.4 * impact - 0.2 * risk) * 10 / 8reasoning: 2-3 sentences explaining the verdictrevisions: specific changes needed (ifREVISE)decomposition: list of concrete tasks (ifAPPROVE)
Rules
- Be skeptical by default; the bar for
APPROVEis high. - Only
APPROVEproposals withcomposite_score >= 7. REVISEmeans "good idea, wrong execution"; provide specific fixes.REJECTmeans "not worth doing"; explain why clearly.- Decomposition tasks must be concrete enough for an agent to execute.
- Don't soften your verdicts to be polite.
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 · 45 lines · 13 tokens per session scan A 571e127461e7
analyst 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 445 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…