consensus-loop

Plugin consensus-loop in berrzebb/consensus-loop. Commands read from the repo's manifest — 1 month ago.

Skills (9)

• consensus-loop:audit

  Run a consensus-loop audit manually — Codex reviews pending trigger_tag items in the watch file. Use when you want to trigger an audit without editing the watch file, re-run a failed audit, or test the audit prompt.

• consensus-loop:guide

  Guide for writing evidence packages for the consensus-loop watch file. Use when preparing code review submissions, structuring feedback evidence, or addressing audit rejections.

• consensus-loop:tools

  Run consensus-loop deterministic analysis tools via CLI — code_map, dependency_graph, audit_scan, coverage_map, rtm_parse, rtm_merge, audit_history, fvm_generate, fvm_validate. Use this skill whenever you need codebase analysis (symbol index, dependency DAG, pattern scan, coverage), RTM operations (

• consensus-loop:merge

  Squash-merge a worktree branch into the target branch with a structured commit message. Use after audit consensus and retrospective completion.

• consensus-loop:orchestrator

  Session orchestrator for the consensus-loop — reads handoff, picks unblocked tasks, distributes to parallel workers, tracks agent assignments, manages correction cycles via SendMessage. Use when starting a work session with pending tasks, distributing implementation work, or reviewing completed work

• consensus-loop:planner

  Design tasks into tracks with work breakdowns and execution order. Also writes and maintains PRDs (Product Requirements Documents) — when a user requests a feature, analyzes it, adds it to the PRD, then decomposes into work breakdowns. Use for new feature planning, PRD writing, architecture changes,

• consensus-loop:retrospect

  Extract learnings from audit history and conversation, manage memories, clean up stale entries. Use after completing a track, during retrospective (③ memory step), at end of session, or anytime the user wants memory maintenance. Triggers on 'what did we learn', 'memory cleanup', 'review learnings',

• consensus-loop:status

  Show current consensus-loop status — pending reviews, audit state, retro marker, agent assignments. Use to check what's happening before starting work or after returning from a break.

• quorum:verify

  Run all done-criteria checks (CQ/T/CC/CL/S/I/FV/CV) and produce a pass/fail verification report. Use after implementing code, before submitting evidence to the quorum audit.

Slash commands (9)

• /consensus-loop:cl-guide

  Shortcut for /consensus-loop:guide — evidence writing guide

• /consensus-loop:cl-merge

  Shortcut for /consensus-loop:merge — squash-merge worktree branch

• /consensus-loop:cl-orch

  Shortcut for /consensus-loop:orchestrator — distribute tasks, manage agents

• /consensus-loop:cl-plan

  Shortcut for /consensus-loop:planner — design PRD, tracks, work breakdowns

• /consensus-loop:cl-retro

  Shortcut for /consensus-loop:retrospect — extract learnings, manage memories

• /consensus-loop:cl-tools

  Shortcut for /consensus-loop:tools — run deterministic analysis tools

• /consensus-loop:cl-verify

  Shortcut for /consensus-loop:verify — run done-criteria checks (CQ/T/CC/CL/S/I/FV/CV)

• /consensus-loop:consensus-audit

  Shortcut for /consensus-loop:audit

• /consensus-loop:consensus-status

  Shortcut for /consensus-loop:status

Subagents (3)

• implementer

  Headless worker for quorum — receives task + context, implements code, runs tests, submits evidence to watch file, handles audit corrections. Use when the orchestrator needs to delegate a coding task to a worker agent.

• scout

  Read-only RTM generator — reads all track work-breakdowns, verifies each requirement against the actual codebase using deterministic tools, and produces 3 Requirements Traceability Matrices (Forward, Backward, Bidirectional). Use when the orchestrator needs to establish or update the RTM before dist

• ui-reviewer

  Find UI issues that code-level analysis (scout, code_map, dependency_graph) cannot detect. Launches a real browser to check rendering, visual states, interactions, a11y, and runtime errors. Use after FE implementation to catch issues invisible to static analysis.

MCP servers (1)

• consensus-loop

  runs: node scripts/mcp-server.mjs

Hooks (12)

• SessionStart

  node ${CLAUDE_PLUGIN_ROOT}/session-start.mjs

• Stop

  node ${CLAUDE_PLUGIN_ROOT}/session-stop.mjs

• PreToolUse

  node ${CLAUDE_PLUGIN_ROOT}/session-gate.mjs

• PostToolUse

  node ${CLAUDE_PLUGIN_ROOT}/index.mjs

• PreCompact

  node ${CLAUDE_PLUGIN_ROOT}/pre-compact.mjs

• PostCompact

  node ${CLAUDE_PLUGIN_ROOT}/post-compact.mjs

• SubagentStart

  node ${CLAUDE_PLUGIN_ROOT}/subagent-start.mjs

• SubagentStop

  node ${CLAUDE_PLUGIN_ROOT}/subagent-stop.mjs

• WorktreeCreate

  node ${CLAUDE_PLUGIN_ROOT}/worktree-create.mjs

• WorktreeRemove

  node ${CLAUDE_PLUGIN_ROOT}/worktree-remove.mjs

• TeammateIdle

  node ${CLAUDE_PLUGIN_ROOT}/teammate-idle.mjs

• TaskCompleted

  node ${CLAUDE_PLUGIN_ROOT}/task-completed.mjs

Similar plugins