beads-swarm
Execute beads with parallel agent swarm (dependency-aware)
A command is the one you type. It runs exactly when you ask it to, and never before.
1,184 commands across 626 plugins.
Execute beads with parallel agent swarm (dependency-aware)
Add statusline configuration to Claude settings file
Run a WoterClip heartbeat cycle (pick up issues, do work, report)
Initialize WoterClip in this repo (config, personas, GitHub labels)
Show WoterClip status (queue, blocked issues, last heartbeat)
Autonomous session-orchestration loop with kill-switches (Phase C-1.b — all 10 kill-switches shipped)
Multi-story autopilot orchestrator — runs N parallel issue pipelines in isolated git worktrees (v3.6 Phase D thin-slice)
Scaffold the minimum repo structure required by session-orchestrator
This file is Read inline by agents that surface findings to the user after deep research. It defines the translation rule that prevents bare identifiers (table…
**Before reading further, print this status line so the user sees a progress signal during the upcoming reasoning pass:**
This file holds the complete worked examples of a good alignment gate - a finding presented to the user, end to end. Two kinds of finding exist, and each has…
Run the scoped deep literature loop until relevant papers are saturated.
Orchestrate the experiment auditor/scientist/coder/reviewer loop for a workspace.
Create or continue ideas from a topic and run create/review/refine/deep-lit to dual-gate saturation.
Capture one genuine architecture decision as a thin, human-confirmed ADR under docs/superpowers/adr/NNNN-slug.md — decision-with-alternatives-and-consequences,…
Run Compound V Phase 1A — code archaeology — on a topic without running the other pre-flights. Useful when you want the technical audit but already have domain…
Re-run the collect + scope-gate + review tail of a Compound V run by run-id. Normalizes each job's output into results/<id>.json, re-runs the git-derived scope…
Front-end problem diagnosis and repair: covering build failures, runtime errors, UI exceptions, and interface problems, using a unified diagnostic framework to…
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
Initialize frontend-craft project template, rules or downgrade instructions according to the current AI runtime.
Audit agents spawned in the current/last run against the agent-selection taxonomy
Run the Agent Diversity Review gate and emit the result table
Meta-analyze the effectiveness of a /loop arc — per-iteration metrics, LOC delta trend, saturation detection, and a keep/lengthen/delete recommendation.
Analyze tech stack, run dev tooling, and remediate code quality issues
Extract lessons learned, update CONSIDERATIONS.md, and maintain SECURITY-COMPLIANCE.md between phases
Pull, version-bump, commit all changes, and push to origin
Generate or modify Metin2 client UI code via the m2ui skill (screenshots, descriptions, existing scripts, audits)
Implement tasks from a conversation's specs (Experimental)
Archive a completed change in the experimental workflow
Advance Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build [sprint]
Advance parallel Generator-side actions only. Auto-selects contract, build, or fix from status.md. /auto-harness:build-parallel [sprint]
Run the full Auto-Harness orchestration flow. /auto-harness:harness <brief or clarification/spec-approval reply>
Process delegation requests from agents and orchestrate multi-agent workflows.
Plan a new feature using spec-workflow-orchestrator skill
Show current project implementation status
© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic