claude

spec-autopilot

Spec-driven autopilot orchestration for delivery pipelines with 8-phase workflow, 3-layer gate system, and crash recovery

3 on GitHubby vibeflow-teamv5.15.3MITupdated 3 months agodevelopment
/

Plugin spec-autopilot from marketplace stoicatom-plugins in stoicatom/claude-autopilot. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (22)

  • autopilot-agents

    Use when the user wants to discover, install, list, hot-swap, or get recommendations for phase-specific autopilot sub-agents sourced from community catalogs (OMC, Anthropic official, VoltAgent, etc.), or when the autopilot setup flow needs to resolve a missing agent for a given phase.

  • autopilot-dispatch

    Use when the autopilot orchestrator main thread is about to dispatch a phase-specific sub-agent via the Task tool and needs the JSON envelope contract, explicit path injection, and parameterized prompt templates. Not for direct user invocation; skip when the current context is not the autopilot orch

  • autopilot-docs-fix

    Use when the user runs /autopilot-docs-fix scan|apply or asks to convert documentation drift candidates into git-applicable patches or manual suggestion templates under human confirmation.

  • autopilot-docs-sync

    Use when the autopilot orchestrator or pre-commit hook needs deterministic static detection of documentation drift between SKILL.md, runtime scripts, CLAUDE.md and their README / .dist-include / root plugin table targets.

  • autopilot-gate

    Use when an autopilot phase boundary is reached and gate verification + checkpoint + event emission are required before advancing to the next phase.

  • autopilot-learn

    Use when the autopilot orchestrator has finished Phase 7 archive and needs to aggregate Episode records into the L1/L2/L3 learning tiers, cluster failure/success patterns, and emit L3 promotion candidates. ONLY for autopilot orchestrator; not for direct user invocation.

  • autopilot-models

    Use when the user wants to view or change the per-phase AI model routing strategy for autopilot — for example choosing a cost-optimized, balanced, or quality-max preset, inspecting the current routing table, or customising an individual phase's model binding.

  • autopilot-phase0-init

    Use when the autopilot orchestrator main thread enters Phase 0 to bootstrap a session (env checks, config load, recovery decision, lockfile, anchor commit). Not for direct user invocation.

  • autopilot-phase1-requirements

    Use when autopilot orchestrator enters Phase 1 to understand requirements, drive multi-round clarification, and produce the structured requirement packet checkpoint.

  • autopilot-phase2-3-openspec

    Use when the autopilot orchestrator main thread reaches Phase 2 or Phase 3 and must dispatch the mechanical OpenSpec change creation and Fast-Forward artifact generation as background tasks against the prepared requirements bundle.

  • autopilot-phase4-testcase

    Use when the autopilot orchestrator enters Phase 4 to design test cases. Applies after Phase 3 alignment with tasks.md ready; gates Phase 5 dispatch.

  • autopilot-phase5-5-redteam

    Use when the autopilot orchestrator has completed Phase 5 implementation and must run a Red Team adversarial critic pass before Phase 6 reporting begins, validating the implementation against attack scenarios. ONLY for autopilot orchestrator; not for direct user invocation.

  • autopilot-phase5-implement

    Use when the autopilot orchestrator enters Phase 5 after Phase 4 test case design has been approved and is about to choose an implementation path (parallel, serial, or TDD) and dispatch implementation work.

  • autopilot-phase6-report

    Use when the autopilot orchestrator reaches Phase 6 after Phase 5.5 Red Team has passed and must generate test reports with tri-path parallel execution covering testing, code review, and quality scans before archival.

  • autopilot-phase7-archive

    Use when the autopilot orchestrator reaches Phase 7 after Phase 6 tri-path reports are available and must finalize the delivery by collecting summaries, extracting knowledge, previewing Allure, and evaluating archive readiness.

  • autopilot-recovery

    Use when the autopilot orchestrator restarts after a crash or interruption and must scan existing checkpoints, detect partial state, and determine the safe resume point. Not for direct user invocation; skip outside the orchestrator main thread.

  • autopilot-risk-scanner

    Use when the autopilot orchestrator dispatches an adversarial Critic sub-agent just before a phase gate and needs that sub-agent to score the phase artifacts against structured rubrics and emit risk-report-phase{N}.json into the change context for downstream gate prechecks. ONLY for autopilot orches

  • autopilot-setup

    Use when a user initializes autopilot in a project that lacks .claude/autopilot.config.yaml, requests /autopilot-setup, asks to bootstrap autopilot configuration, or needs autopilot to detect project tech stack, services, agents, and test suites for the first time.

  • autopilot-test-audit

    Use when the user wants a read-only static audit of test rot — for example asks to '检测测试腐烂' or 'audit tests', suspects deleted runtime scripts are still referenced in tests, hook files were renamed, weak assertions or duplicate case names may have crept in, or a candidate list at .cache/spec-autopil

  • autopilot-test-fix

    Use when the user wants to consume the test-rot candidate list at .cache/spec-autopilot/test-rot-candidates.json and generate repair artifacts — deterministic sed-style patches for R1 orphan references and .suggestion.md files (including weak-assertion templates) for the rest. Typical triggers: '/au

  • autopilot-test-health

    Use when the user wants to quantify test effectiveness — running lightweight shell-layer mutation testing and static health scoring to confirm the test suite would actually catch regressions. Typical triggers include weekly CI sweeps, on-demand audits asking 'how healthy are our tests', or '/autopil

  • autopilot

    Use when the user requests an end-to-end spec-driven delivery pipeline (requirements → OpenSpec → implementation → testing → archive); orchestrates Phase 0-7.

Hooks (25)

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/guard-no-verify.sh

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/guard-ask-user-phase.sh

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh PreToolUse

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/check-predecessor-checkpoint.sh

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/auto-emit-agent-dispatch.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh PostToolUse

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/emit-tool-event.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/post-task-validator.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/validate-phase1-envelope.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/auto-emit-agent-complete.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/unified-write-edit-check.sh

  • PreCompact

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh PreCompact

  • PreCompact

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/save-state-before-compact.sh

  • UserPromptSubmit

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh UserPromptSubmit

  • Stop

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh Stop

  • SubagentStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh SubagentStart

  • SubagentStop

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh SubagentStop

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh SessionStart

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/scan-checkpoints-on-start.sh

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/auto-install-statusline.sh

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/check-skill-size.sh

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh PostCompact

  • SessionStart

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/reinject-state-after-compact.sh

  • SessionEnd

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/capture-hook-event.sh SessionEnd

  • SessionEnd

    bash ${CLAUDE_PLUGIN_ROOT}/runtime/scripts/stop-gui-on-session-end.sh

View source on GitHub

More from stoicatom/claude-autopilot

All 5 plugins →

Parallel AI engineering control-plane plugin with task-graph scheduling, file ownership isolation, cost-aware model routing, 9-gate system, RBAC governance, and audit trail

4 skills · hooks

3

Auto-generate and submit daily work reports from git commits and Lark chat history

1 skill

3

Translate Figma designs into production-ready code with 1:1 visual fidelity. Adapted from OpenAI's official figma-implement-design skill, with Claude Code-native MCP integration and design system token mapping.

1 skill

3

slim-task

claude

Structured 7-phase task execution SOP with multi-language and worktree support — session init, requirements clarification, best-practice research, impact scoping, DAG-based parallel dispatch, blind-audit quality review by independent sub-agents, commit confirmation

1 skill

3

Similar plugins

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Maintain spec-autopilot?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins5 plugins