slim-task

中文版 | English (default)

stoicatom-plugins

A Claude Code plugin marketplace — spec-driven autopilot orchestration and parallel AI engineering control-plane.

Plugins

Plugin	Version	Description
spec-autopilot	5.15.3	Spec-driven autopilot orchestration for delivery pipelines — 8-phase workflow with 3-layer gate system and crash recovery
parallel-harness	1.9.1	Parallel AI engineering control-plane — task-graph scheduling, 9-gate system, RBAC governance, cost-aware model routing
daily-report	1.3.0	Auto-generate and submit daily work reports from git commits and Lark chat history
figma-codegen	1.0.0	Translate Figma designs into production-ready code with 1:1 visual fidelity (adapted from OpenAI figma-implement-design)
slim-task	0.8.1	Structured 7-phase task execution SOP with multi-language & worktree support — session init, requirements clarification, impact scoping, DAG-based parallel dispatch, blind-audit quality review

Quick Install

# 1. Add marketplace
claude plugin marketplace add stoicatom/claude-autopilot

# 2. Install spec-autopilot (project-level)
claude plugin install spec-autopilot@stoicatom-plugins --scope project

# 3. Install parallel-harness (project-level)
claude plugin install parallel-harness@stoicatom-plugins --scope project

# 4. Install daily-report (project-level)
claude plugin install daily-report@stoicatom-plugins --scope project

# 5. Install figma-codegen (project-level)
claude plugin install figma-codegen@stoicatom-plugins --scope project

# 6. Install slim-task (project-level)
claude plugin install slim-task@stoicatom-plugins --scope project

# 7. Restart Claude Code

What is spec-autopilot?

spec-autopilot is a Claude Code plugin that automates the full software delivery lifecycle: from requirements gathering through implementation, testing, reporting, and archival.

Key Features

• 8-Phase Pipeline — Requirements → OpenSpec → FF Generate → Test Design → Implementation → Test Report → Archive
• 3-Layer Gate System — TaskCreate dependencies + Hook checkpoint validation + AI checklist verification
• Crash Recovery — Automatic checkpoint scanning and session resume
• Anti-Rationalization — 16 pattern detection to prevent sub-agents from skipping work
• TDD Cycle — RED-GREEN-REFACTOR with deterministic L2 validation
• Requirements Routing — Auto-classify as Feature/Bugfix/Refactor/Chore with dynamic gate thresholds
• Event Bus — Real-time event streaming via events.jsonl + WebSocket
• GUI V2 Dashboard — Three-column real-time dashboard with decision_ack feedback loop
• Parallel Execution — Domain-level parallel agents with file ownership enforcement
• Modular Test Suite — 104 test files with 1245+ assertions

Architecture

graph TB
    subgraph "Main Thread (Orchestrator)"
        P0[Phase 0: Environment Check<br/>+ Crash Recovery]
        P1[Phase 1: Requirements<br/>Multi-round Decision Loop]
        P7[Phase 7: Summary<br/>+ User-confirmed Archive]
    end

    subgraph "Sub-Agents (via Task tool)"
        P2[Phase 2: Create OpenSpec]
        P3[Phase 3: FF Generate]
        P4[Phase 4: Test Design]
        P5[Phase 5: Implementation<br/>Serial / Parallel / TDD]
        P6[Phase 6: Test Report]
    end

    P0 --> P1
    P1 -->|Gate| P2
    P2 -->|Gate| P3
    P3 -->|Gate| P4
    P4 -->|Gate| P5
    P5 -->|Gate| P6
    P6 --> P7

    style P0 fill:#e1f5fe
    style P1 fill:#e1f5fe
    style P7 fill:#e1f5fe
    style P4 fill:#fff3e0
    style P5 fill:#fff3e0

What is parallel-harness?

parallel-harness is a Claude Code plugin that provides a task-graph-driven parallel AI engineering platform. It enables multi-agent orchestration with strict governance, cost control, and quality gates.

Key Features