AbsoluteZero

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

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.

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 worker output.

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 (parse, merge, query), or FVM operations (generate matrix, validate against server) — even if the MCP server is not configured. This skill replaces mcp__plugin_consensus-loop_consensus-loop__* tool calls with equivalent CLI commands.

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

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', 'retrospective', 'update memories', '회고', '메모리 정리'.

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, multi-track decomposition, requirements analysis, or adjusting existing execution plans. Trigger when user says things like 'add feature X', 'I need Y', 'plan Z', or describes any product requirement.

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 distributing work.

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.

Feature or requirement description

Optional: track name or 'all'

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.

Optional task ID to assign

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.

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.

Optional: specific category (CQ, T, CC, CL, S, I, FV, CV)

Tool name + args (e.g., 'code_map --path src/')

Target branch (default: main)

Flags: --dry-run, --no-resume, --auto-fix, --model <name>

Shortcut for /consensus-loop:status

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