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/bernstein-create-tasknpx skills add sipyourdrink-ltd/bernstein --skill bernstein-create-taskgit 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/bernstein-create-task)<a href="https://agentmods.dev/skills/sipyourdrink-ltd/bernstein/bernstein-create-task"><img src="https://agentmods.dev/badge/skills/sipyourdrink-ltd/bernstein/bernstein-create-task.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 | $0.00047 | $0.00400 |
| Opus 5 | $0.00023 | $0.00200 |
| Sonnet 5 | $0.00009 | $0.00080 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
bernstein-create-task 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
Create Bernstein Task
Create a new task in the Bernstein orchestrator and have it picked up by an agent.
When to Use
- User says "create a task for..." or "add this to bernstein"
- User wants to delegate a coding task to an agent
- User describes a bug fix, feature, or refactor that should be orchestrated
- User says "have an agent do this" or "queue this up"
Instructions
-
Ask the user (if not already clear) for:
- Title: short description of the task
- Role: one of
backend,frontend,qa,security,devops,docs(default:backend) - Priority: 0 (urgent) to 3 (low) (default: 1)
- Scope:
tiny,small,medium,large(default:small)
-
Run
scripts/create-task.shwith the task details:scripts/create-task.sh "Fix the auth middleware to handle expired tokens" backend 1 small -
Show the created task ID and confirm it's queued:
Task TASK-042 created (role=backend, priority=1) An agent will pick it up shortly. -
If the user wants to track it, suggest using
/bernstein-status.
Tips
- For complex tasks, suggest breaking them into smaller subtasks
- For risky changes, add
--require-reviewflag - High-priority (0) tasks get picked up immediately
What ships with it
1 file 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.
- 5d ago First seen · 46 lines · 47 tokens per session scan A e1e4a23c9f8a
bernstein-create-task is a skill published in the GitHub repository sipyourdrink-ltd/bernstein (1,038 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 400 once invoked, about $0.0002 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
linear
Manage issues, projects & team workflows in Linear. Use when the user wants to read, create or updates tickets in Linear.
git-workflow
Trunk-based git workflow with worktrees, switch/restore over checkout, Conventional Commits, force-with-lease. Use whenever the user asks me to commit, push, branch, or rebase.
project-briefing
Generate an executive briefing of the last 24 hours of commits for the current project or a specified directory. Use when the user asks for a project update, daily briefing, commit summary, "what changed today," or wants to stay up-to-date with recent work.
split-to-prs
Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
issue
Create a GitHub issue using the Dedalus issue templates (bug, feature, question). Injects branch and commit context automatically, prompts for Linear link. Use when creating a GitHub issue using Dedalus templates, or the user says "file an issue", "create issue", "open a bug", or "report a feature request".
flow-parallel
Decompose and execute large changes, migrations, or multi-issue fixes in parallel with quality gates.