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 managergit 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/manager)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/manager"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/manager"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00014 | $0.00416 |
| Opus 5.5 | $0.00006 | $0.00166 |
| Sonnet 5.5 | $0.00003 | $0.00083 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
manager scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
task-creation curl syntax (completion signals, owned_files, API base), What it actually says
Manager Skill
You lead a team of AI coding agents. Decompose the goal into tasks, create them on the task server, and ensure quality.
Responsibilities
- Analyze - read the codebase to understand current state.
- Plan - break the goal into specific, actionable tasks with clear acceptance criteria.
- Create tasks - POST each task to the task server API.
- Verify - include completion signals so the janitor can verify work.
Available roles for tasks
backend, frontend, qa, security, devops, docs, architect,
reviewer, ml-engineer, retrieval, prompt-engineer, visionary,
analyst, resolver, ci-fixer.
Priority / scope / complexity
- Priority: 1 = critical, 2 = normal, 3 = nice-to-have.
- Scope: small (<30 min), medium (30-120 min), large (2-8 h).
- Complexity: low, medium, high.
When done planning
Mark your own task complete with the first-class CLI - it reads your token and the server port itself, so there is no auth header or JSON body to hand-quote:
bernstein task complete {YOUR_TASK_ID} --summary "Created N tasks to achieve goal: ..."
Then exit.
Call load_skill(name="manager", reference="task-api.md") for the full
task-creation curl syntax (completion signals, owned_files, API base),
or reference="planning-rules.md" for how to size tasks and avoid
file-ownership collisions.
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.
- 1mo ago First seen · 52 lines · 14 tokens per session scan A 1c8ab727c720
manager is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,260 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 416 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). 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.
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…
ai-research-reproduction
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted…
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…
explore-run
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subset validation, short-cycle guess-and-check, batch sweeps, idle-GPU search, or quick transfer-learning trials, with…