Skip to content
Development
Skill

/bernstein-run

Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs,

From plugin
bernstein
82026 skills1 agent3 commands1 hook
+1
Install
$ npx -y skills add sipyourdrink-ltd/bernstein --skill bernstein-run --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/bernstein-run

Context preview

The summary Claude sees to decide when to auto-load this skill.

Run a verified multi-agent goal with Bernstein. Use when a task is too large for a single agent session: Bernstein decomposes the goal into tasks, spawns CLI coding agents in parallel git worktrees, verifies their output, and merges results. Also use to check run status, costs,

SKILL.md

bernstein-run.SKILL.md
name: bernstein-run
description: >
  Run a verified multi-agent goal with Bernstein. Use when a task is too
  large for a single agent session: Bernstein decomposes the goal into
  tasks, spawns CLI coding agents in parallel git worktrees, verifies
  their output, and merges results. Also use to check run status, costs,
  and to verify a finished run against its lineage and audit chain.

Run a verified multi-agent goal

Bernstein is a deterministic multi-agent orchestrator for CLI coding agents. This skill wraps the three-step operator loop: submit a goal, monitor progress, and verify the finished run against its Merkle-chained lineage journal and HMAC audit chain.

Prerequisites

  • `bernstein` on PATH (`pip install bernstein` or `uv tool install bernstein`).
  • Run commands from the project root (the directory holding `.sdd/` after

the first run).

  • First-time setup: `bernstein init` scaffolds config and templates.

Workflow

1. Submit

bernstein run -g "<goal>"
  • The goal is a plain-English description of what to build or fix.
  • Bernstein plans tasks, assigns roles (backend, frontend, qa, security,

devops), and spawns agents in isolated git worktrees.

  • Preview without spending: `bernstein run --dry-run -g "<goal>"`.

2. Monitor

bernstein status
bernstein cost
  • `status` shows task summary and agent health.
  • `cost` shows the spend so far against configured budgets.

3. Verify

bernstein lineage verify <run_id>
bernstein audit verify
  • `lineage verify` recomputes the run's Merkle hash chain and every HMAC

tag; exit 0 means the chain is intact and non-empty.

  • `audit verify` checks the HMAC audit chain and Merkle tree across the

whole workspace; run it before trusting or shipping the result.

Report the run as complete only when both verifications exit 0.

Verifying this skill's own install

Installs of this skill are receipt-backed. To confirm `bernstein` is on PATH and the bundled skill asset resolves in this session:

bernstein skills package show

To prove the skill content the session is driving matches what was installed:

bernstein skills package verify --dest <path-to-this-skill-directory>

Exit 0 means the installed tree's content address matches a receipt anchored in the lineage spine and audit chain. These two commands are the self-check contract the multi-host conformance sweep replays per agent host (`bernstein skills package conformance`).

Notes

  • Never mark a goal done from agent output alone; the lineage and audit

verifications are the completion evidence.

  • If `bernstein` is not installed, say so and point at the prerequisites

above; do not attempt to reimplement orchestration inline.

  • See `references/worked-examples.md` for end-to-end transcripts and

per-host invocation notes.

Read more
Ships withbernstein

Deterministic orchestrator for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). No model in the coordination loop, so parallel runs in per-task git worktrees replay byte-identically. Signed lineage plus an opt-in HMAC audit chain a reviewer checks offline, without rerunning it. Cluster mode, air-gap deploy. https://bernstein.run

Get the whole plugin