Plugin Claude Code
Morning Star — Agent Plugin for harness engineering workflows: a TS Harness Workflow Engine (@mstar-harness/engine) that enforces deterministic workflow gates, plus mstar- judgment skills for multi-agent code delivery across OpenCode, Cursor, Codex, Kimi Code, ZCode, and omp.
Cursor rule Cursor
Maintenance guardrails for Morning Star harness repository in Cursor.
Skill Claude CodeCodexCursor
A Chinese-language evaluation skill for checking whether software tasks are routed to the right agents and project checkpoints.
Instructions file CodexOpenCode
Instructions for btspoony/mstar-harness, covering morning star harness maintenance guide, scope, maintenance goals, core rules and cursor + opencode + codex + kimi + zcode + omp sync policy.
Instructions file
Instructions for btspoony/mstar-harness, a project described as: An omni-plugin for harness engineering workflows with multi-agents, programmatic gates and skills.
Agent
A technical architecture role for designing systems, making technical decisions, and writing technical documents. ADR means a written record of an important architecture decision.
Agent
A read-only code reviewer for SDD task reviews and codebase audits. SDD is a way to define and deliver software through structured tasks and design information.
Agent
前端开发工程师 - 页面/组件/交互/a11y/前端性能。全栈功能里默认前端主责（与 @fullstack-dev 分轨）；纯 UI 任务首选本角色。 Frontend Developer - pages/components/interactions/accessibility/frontend performance. This is the default frontend owner in fullstack work (split with @fullstack-dev) and the preferred role for pure UI tasks.
Agent
A second full-stack development role for work that can run alongside another developer’s track. Full-stack work covers both application interfaces and server-side code.
Agent
A backend-led full-stack development role for implementing APIs, business logic, data layers, and related frontend work. Full-stack means work that spans both the user interface and server-side systems.
Agent
运维工程师 - 部署、监控和基础设施。 Ops Engineer - deployment, monitoring, and infrastructure operations, including CI/CD and observability.
Agent
A product-planning role for understanding needs, defining products, researching users and markets, and writing product documents. It focuses on deciding what should be built and why.
Agent
项目经理 - 协调开发团队，管理项目进度。 Project Manager - coordinate the team, track progress, and orchestrate execution across roles.
Agent
提示词工程师 - 设计与优化 Agent 提示词与技能。 Prompt Engineer - design and optimize prompts and skills for agents, including refactoring and debugging prompt systems.
Agent
测试工程师 - L4 验收席（分级派发）：DoD 映射、residual 验证、report-only 调查。 QA Engineer - tiered L4 acceptance (DoD mapping, residual verify, report-only); dispatched when PM sets QA gate mandatory.
Agent
质量控制专家（Reviewer #2）- 代码审查（diff / 逻辑 / 安全正确性）。非测试执行席。 Quality Control Specialist (Reviewer #2) - code review (diff, logic, security/correctness). Not a test runner.
Agent
质量控制专家（Reviewer #3）- 代码审查（diff / 逻辑 / 性能可靠性）。非测试执行席。 Quality Control Specialist (Reviewer #3) - code review (diff, logic, performance/reliability). Not a test runner.
Agent
A code-review role focused on changes, program logic, and whether the architecture will remain maintainable. It is a reviewer, not a person who runs tests.
Agent
A writing-focused subagent for documentation, fiction, copywriting, and scripts. The description says it must first load shared workflow and role instructions before working.
Command
Deep, pre-merge review of a PR / branch / diff at three strengths — quick / default (default) / deep — one verdict, posted to GitHub when a PR number is given. Decides whether a change is safe to ship with evidence-backed findings, rather than a shallow "looks good" pass. Produces a ship it / needs fixes / blocked…
Command
Survey a codebase as a senior advisor and produce prioritized, self-contained improvement plans. Read-only on source code. Use standalone before iteration-start to discover what's worth doing, or independently to build a prioritized backlog.
Command
Drive the active iteration to completion — Phase 2 Autonomous Execute, Phase 3 iteration-close, Phase 4 Create PR, Phase 5 PR merge-ready loop (prefer babysit/-babysit; optional greploop when repo has it; else CI fallback) until mergeable. Not Done until Phase 5 exit checklist passes.
Command
Autonomous full iteration loop for cloud agents — Phase 1 (code-first auto direction lock + compass/plans + Review & Edit chain) through Phase 2–5 (execute → close → PR → merge-ready). Optional args: direction, scale (S|M|L|XL, default M). Not Done until Phase 5 exit checklist passes. Minimal human intervention; no…
Command
Start a new harness iteration — optional direction hint, research, grill-me, compass/plans, Review & Edit chain (long-lived {SPECSDIR}/ + {ITERATIONDIR}/ / package; compound promotes package at close only), PM lock, integration branch; then auto-continue Phase 2→5 (execute → close → PR → merge-ready) unless pause arg…