quantum-loop

**Activation:** runs after main loop exits (always-on).

Detects sequential bottlenecks in the dependency DAG and proposes restructuring. Analyzes linear chains, single-story waves, and fan-out blockers. Spawned by the dag-validator coordinator.

Computes complete fileConflicts from task filePaths intersections with severity classification. Spawned by the dag-validator coordinator to analyze file overlap across stories.

You are the **per-wave coordinator** for quantum-loop. Each invocation handles exactly ONE wave from quantum.json's DAG, then exits. The parent shell (`quantum-loop.sh --coordinator`) re-spawns you for the next wave.

**Activation guard:** `lib/intent-graph.sh` is sourced AND `INTENT_GRAPH_AVAILABLE=true`.

Coordinator agent that spawns specialist sub-agents (bottleneck-analyzer, duplication-detector, conflict-auditor) to validate and restructure the DAG produced by ql-plan. Detects sequential bottlenecks, functional duplication, and incomplete fileConflicts. Auto-restructures with cycle detection and creates stub stories for the planner to flesh out.

Detects stories with overlapping implementation concerns using hybrid keyword pre-filter and LLM semantic verification. Spawned by the dag-validator coordinator.

Per-story implementation agent. Implements exactly ONE user story from quantum.json following TDD methodology. Spawned fresh for each story with no memory of previous iterations.

**Activation:** runs at every wave boundary (no module-availability guard).

**Activation:** runs after Step 4B passes (always-on; no-op when `execution.discoveredContracts` is empty).

**Activation guard:** `lib/dead-code.sh` is sourced AND `DEAD_CODE_AVAILABLE=true`.

**Activation:** runs after Step 4 passes (always-on; Step 4B.5 deep-review dispatch is gated by `should_dispatch_deep_review`).

**Activation guard:** `lib/hyclone.sh` is sourced AND `HYCLONE_AVAILABLE=true`.

**Activation:** runs at orchestrator init (always-on; degrades gracefully when libs absent).

**Activation:** reference documentation; consulted when reading/writing the relevant `execution.*` substructures.

**Activation guard:** `lib/reground.sh` is sourced AND `REGROUND_AVAILABLE=true`.

**Activation guard:** `lib/skeleton.sh` is sourced AND `SKELETON_AVAILABLE=true`.

**Activation guard:** `lib/deslop.sh` is sourced AND `DESLOP_AVAILABLE=true` AND story.deslop.skip != true.

**Activation:** runs at every wave boundary (uses `lib/type-audit.sh` directly; degrades gracefully when functions absent).

---

---

---

Short-lived agent that consolidates duplicate type definitions found across parallel stories. Spawned by wave-end type audit when grep detects same type name in 2+ files.

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Deep Socratic exploration of a feature idea before implementation. Asks questions one at a time, proposes 2-3 alternative approaches with trade-offs, presents design section-by-section for approval, and saves an approved design document. Use when starting a new feature, exploring an idea, or before writing a spec. Triggers on: brainstorm, explore idea, design this, think through, ql-brainstorm.

Multi-perspective post-implementation review aggregator for quantum-loop. Invokes 2-7 reviewer agents in parallel based on risk score, applies actionability filter, dedups, aggregates with evidence requirements. Use AFTER the per-story two-stage review gates pass and before merging a whole-feature PR to master. Complements ql-review (per-story) with whole-feature review.

Post-review AI-slop cleanup pass. After quality review approves a story/feature, scans only the changed files for: duplicate code, dead code, needless abstraction, boundary violations, missing tests. Proposes deletions with regression-test gate — rolls back on regression. Mandatory unless explicitly skipped via --no-deslop. Borrowed from OMC Ralph 7.5 + 7.6.

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Run the autonomous execution loop. Reads quantum.json, queries the dependency DAG, implements stories with TDD and two-stage review gates. Supports parallel execution via native worktree isolation. Use after /quantum-loop:plan has created quantum.json. Triggers on: execute, run loop, start building, ql-execute.

Detect repo-hygiene issues that accumulate during long-running autonomous development (merge-conflict markers, orphan worktrees, CPC-variant duplicates, stale branches, version-manifest drift). Detection-only by default — reports findings, never deletes or modifies without explicit user confirmation.

Intent-drift audit for quantum-loop. Compares the user's original intent (immutable snapshot) against downstream artifacts (design.md → PRD → quantum.json ACs → implementation) to detect semantic divergence. Flags drift with file:line evidence. Use before merge or when specs feel "rewritten."

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Convert a PRD into machine-readable quantum.json with dependency DAG, granular 2-5 minute tasks, and execution metadata. Use after creating a spec with /quantum-loop:spec. Triggers on: create plan, convert to json, plan tasks, generate quantum json, ql-plan.

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Two-stage code review. Spec compliance first, then code quality. Use after implementation or before merge. Triggers on: review code, code review, check implementation, ql-review.

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Generate a structured Product Requirements Document (PRD) with user stories, acceptance criteria, and functional requirements. Use when you have an approved design and need formal requirements, or when starting from scratch. Triggers on: create spec, write prd, spec out, requirements for, ql-spec.

Part of the quantum-loop autonomous development pipeline (brainstorm → spec → plan → execute → review → verify). Iron Law verification gate. Requires fresh evidence before any completion claim. Use before claiming work is done, before committing, or before marking a story as passed. Triggers on: verify, check, prove it works, ql-verify.