跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
设计与 UI

autobuild

Autonomous single-shot plan execution. Runs entire superplan implementation plans without stopping, using sub-agents for each phase. Phases write state to filesystem for resume capability. Sequential phases run in order, parallel phases (1a, 1b) run concurrently. User never needs to compact context.

asteroid-belt · 已有静态检查记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add asteroid-belt/skulto --skill autobuild

技能说明


name: autobuild description: Autonomous single-shot plan execution. Runs entire superplan implementation plans without stopping, using sub-agents for each phase. Phases write state to filesystem for resume capability. Sequential phases run in order, parallel phases (1a, 1b) run concurrently. User never needs to compact context. metadata: version: "1.0.0" author: skulto compatibility: Requires plan document in superplan format. Sub-agents execute phases independently. State persisted to .autobuild/ directory.

Autobuild: Autonomous Plan Execution Engine

Execute entire implementation plans in a single pass with zero user intervention. Each phase runs in its own sub-agent, writing state to the filesystem. Context never exhausts because sub-agents are isolated.

Overview

Autobuild is an autonomous execution engine for superplan implementation plans. Unlike superbuild which stops after each phase for user confirmation, autobuild runs everything to completion.

Key Differences from superbuild:

Aspectsuperbuildautobuild
ExecutionPhase-by-phase with stopsContinuous until complete
User interventionRequired after each phaseNone (fully autonomous)
Context managementManual compactionSub-agents isolate context
State persistenceIn conversationFilesystem (.autobuild/)
Resume capabilityManualAutomatic from state files

Reference Index - MUST READ When Needed

References contain detailed templates and patterns. Read BEFORE you need them.

WhenReferenceWhat You Get
Step 1: InitializeSTATE-FILES.mdState file format, directory structure
Step 3: Execute phasesPHASE-EXECUTION.mdPhase ordering, parallel detection, retry logic
Step 3: Launch sub-agentsSUBAGENT-PROMPTS.mdExact prompts for phase sub-agents
Step 4: Verify and commitVERIFICATION.mdFresh verification, commit handling
Step 5: Handle failuresFAILURE-HANDLING.mdRetry logic, error recovery
Overall flowORCHESTRATION.mdMain orchestration loop, completion handling

Also reference superplan/superbuild documents:

  • superplan/references/TASK-MICROSTRUCTURE.md - TDD 5-step format per task
  • superplan/references/TDD-DISCIPLINE.md - TDD enforcement rules
  • superbuild/references/ENFORCEMENT-GUIDE.md - Quality gate commands by stack, evidence requirements
  • superbuild/references/PLAN-UPDATES.md - Plan checkbox patterns, status updates

DO NOT SKIP REFERENCES. They contain exact prompts, templates, and formats that are NOT duplicated here.


CLI Arguments

/autobuild <plan-path> [options]

Arguments:
  plan-path           Path to superplan document (required)

Options:
  --commit=<mode>     Git commit behavior (required before execution)
                      - auto: Auto-commit after each phase passes
                      - message-only: Generate messages, user handles git
                      - single: One combined commit at the end

  --resume            Resume from existing state (default if .autobuild/ exists)
  --fresh             Ignore existing state, start from scratch
  --dry-run           Validate plan and show execution order without running

Example invocations:

/autobuild docs/feature-plan.md --commit=auto
/autobuild docs/feature-plan.md --commit=message-only --resume
/autobuild docs/feature-plan.md --commit=single --fresh

Critical Workflow

+-----------------------------------------------------------------------+
|                      AUTOBUILD EXECUTION FLOW                          |
+-----------------------------------------------------------------------+
|                                                                       |
|  1. INITIALIZE       |  Parse args, create .autobuild/, detect stack  |
|         |            |  NO PLAN = EXIT (ask user, then exit if none)  |
|         v            |  NO --commit = STOP (require commit mode)      |
|  2. LOAD STATE       |  Read existing state files if --resume         |
|         |            |  Identify completed phases, pending phases     |
|         v                                                             |
|  2.5 PLAN REVIEW     |  Validate plan before autonomous execution     |
|         |            |  Check: ambiguity, deps, tests, risks, conflicts|
|         v            |  IF concerns → EXIT (autonomous = no recovery) |
|  3. EXECUTE PHASES   |  For each pending phase (or parallel group):   |
|     |                |                                                |
|     |  3a. Launch sub-agent(s) for phase(s)                           |
|     |      - Sequential phases: one sub-agent at a time               |
|     |      - Parallel phases (2a,2b,2c): concurrent sub-agents        |
|     |                                                                 |
|     |  3b. Sub-agent executes:                                        |
|     |      - Read plan section for its phase                          |
|     |      - Follow TDD micro-structure per task                      |
|     |      - Run quality gates (lint, test, typecheck)                |
|     |      - Update plan checkboxes                                   |
|     |      - Return: status, commit message, files changed            |
|     |                                                                 |
|     |  3c. Write state file for phase                                 |
|         |                                                             |
|         v                                                             |
|  4. VERIFY + COMMIT  |  Re-run quality gates fresh (trust but verify) |
|         |         
阅读完整来源 ↗