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. Cluster mode, air-gap deploy. Status: beta. https://bernstein.run
Skill Claude CodeCodex
Manage Bernstein agents - list active agents, inspect their output, kill stalled agents, or stream live logs. Use when the user asks about agents, wants to see what an agent is doing, or needs to kill one.
Skill Claude CodeCodex
Show active alerts from Bernstein - failed tasks, stalled agents, budget warnings, blocked tasks needing human intervention. Use when the user asks about problems, errors, warnings, or what needs attention.
Skill Claude CodeCodex
Review and approve/reject pending tasks or plans in Bernstein. Use when the user asks about approvals, wants to review agent work, or needs to approve/reject a plan before execution begins.
Skill Claude CodeCodex
Show detailed cost breakdown and budget status for the Bernstein orchestrator. Use when the user asks about spending, budget, cost per model, cost per agent, or wants a cost projection.
Skill Claude CodeCodex
Create a new task in the Bernstein orchestrator. Use when the user wants to add a task, delegate work to an agent, file a bug fix, or queue up work for the orchestrator to handle.
Skill Claude CodeCodex
Create and manage multi-step execution plans in Bernstein. Plans decompose complex goals into stages with dependencies. Use when the user wants to plan a complex feature, break down a large task, or review an execution plan before agents start working.
Skill Claude CodeCodex
Show quality metrics for Bernstein runs - success rates per model, lint/test pass rates, completion time distributions. Use when the user asks about quality, reliability, which model performs best, or pass rates.
Skill Claude CodeCodex
Show Bernstein orchestrator status - active agents, task progress, costs, and alerts. Use when the user asks about orchestrator status, what agents are doing, task progress, how much has been spent, or what's happening with the build.
Skill Claude CodeCodex
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…
Skill Claude CodeCodex
Evaluate proposals - feasibility, engineering payoff, risk.
Skill Claude CodeCodex
System design - module boundaries, API contracts, ADRs.
Skill Claude CodeCodex
Python server code, APIs, async, strict typing.
Skill Claude CodeCodex
CI failures - read error, minimal fix, verify.
Skill Claude CodeCodex
DevOps - Docker, CI/CD, cloud infra, monitoring.
Skill Claude CodeCodex
Documentation - README, API docs, ADRs, tutorials.
Skill Claude CodeCodex
React / Next.js UI, state, accessibility.
Skill Claude CodeCodex
Planning - decompose goals, create tasks via task server.
Skill Claude CodeCodex
ML - training, inference, embeddings, evaluation.
Skill Claude CodeCodex
LLM prompts - design, evaluate, tune instructions.
Skill Claude CodeCodex
Test writing - pytest suites, edge cases, regressions.
Skill Claude CodeCodex
Git merge conflicts - resolve without losing intent.
Skill Claude CodeCodex
Retrieval - vector DBs, embeddings, hybrid search, reranking.
Skill Claude CodeCodex
Code review - correctness, tests, merge-readiness.
Skill Claude CodeCodex
Security review - OWASP, auth, secrets, input validation.