sipyourdrink-ltd/bernstein

manager

Planning - decompose goals, create tasks via task server.

Langue du texte source : anglais

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…

Langue du texte source : anglais

bernstein-agents

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.

Langue du texte source : anglais

bernstein-alerts

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.

Langue du texte source : anglais

bernstein-plan

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.

Langue du texte source : anglais

bernstein-quality

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.

Langue du texte source : anglais

bernstein-status

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.

Langue du texte source : anglais

architect

System design - module boundaries, API contracts, ADRs.

Langue du texte source : anglais

backend

Python server code, APIs, async, strict typing.

Langue du texte source : anglais

ci-fixer

CI failures - read error, minimal fix, verify.

Langue du texte source : anglais

devops

DevOps - Docker, CI/CD, cloud infra, monitoring.

Langue du texte source : anglais

docs

Documentation - README, API docs, ADRs, tutorials.

Langue du texte source : anglais

frontend

React / Next.js UI, state, accessibility.

Langue du texte source : anglais

ml-engineer

ML - training, inference, embeddings, evaluation.

Langue du texte source : anglais

prompt-engineer

LLM prompts - design, evaluate, tune instructions.

Langue du texte source : anglais

qa

Test writing - pytest suites, edge cases, regressions.

Langue du texte source : anglais

resolver

Git merge conflicts - resolve without losing intent.

Langue du texte source : anglais

retrieval

Retrieval - vector DBs, embeddings, hybrid search, reranking.

Langue du texte source : anglais

reviewer

Code review - correctness, tests, merge-readiness.

Langue du texte source : anglais

security

Security review - OWASP, auth, secrets, input validation.

Langue du texte source : anglais

visionary

Ideation - generate bold feature proposals.

Langue du texte source : anglais

vp

Cross-cell coordination - resolve conflicts, decide pivots.

Langue du texte source : anglais

analyst

Evaluate proposals - feasibility, engineering payoff, risk.

Langue du texte source : anglais

bernstein-approve

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.

Langue du texte source : anglais

bernstein-cost

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.

Langue du texte source : anglais

bernstein-create-task

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.

Langue du texte source : anglais