rlaope/bestwork-agent

trace

Evidence-driven causal tracing — competing hypotheses, falsification, rebuttal round, recommended next probes

validate

Feature validation gate — research, define purpose, stress-test from real user perspective before building

blitz

Maximum parallelism burst — all tasks execute simultaneously with no coordination overhead

deliver

Persistent completion mode — tasks must finish fully with verify/fix loops until done

pipeline-run

Queue and auto-process multiple GitHub issues — each gets its own branch, team, PR, and merge

trio

Execute tasks in parallel with dynamically assigned agents per task

clarify

Ask targeted clarifying questions to uncover missed requirements before execution

superthinking

1000-iteration thought simulation — plan, build, validate, critique, amplify

meetings

Search and browse past meeting logs

waterfall

Sequential staged processing — each stage must pass before the next begins

agents

List all bestwork specialist agent profiles

plan

Analyze task scope and recommend a bestwork team composition before executing

doctor

Diagnose the current project's deploy config vs actual code — find mismatches between what's configured and what exists

delegate

Autonomous execution — classify, allocate, and execute without confirmation

update

Check for updates and upgrade bestwork-agent — plugin cache + hooks + HUD all at once

docs

Sync all documentation (README, docs/, CLAUDE.md) with current codebase state

onboard

First-time setup guide and feature walkthrough

install

Install bestwork hooks into Claude Code

changelog

Auto-generate changelog from git history

health

Quick session health check

review

Check code for hallucinations and platform mismatches

sessions

List Claude Code sessions with stats

status

Show current bestwork-agent configuration