morning-star-harness
v4.5.2by btspoony · author: Bohao Tang
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.
What morning-star-harness does, in the publisher's words
Harness Workflow Engine · Agent Plugin
Morning Star is an Agent Plugin for harness engineering workflows: a TypeScript Harness Workflow Engine (@mstar-harness/engine) enforces deterministic workflow gates, while mstar-* judgment skills drive multi-agent code delivery.
- Deterministic gates, enforced by a TS engine: path/status/lease/dispatch/sdd/iteration/lint gates run in @mstar-harness/engine, not as prompt suggestions
- Judgment stays in mstar-* skills: skills remain the single source of truth (SSOT) for roles, gates, and workflow judgment
- One engine across hosts: the same engine + skills power dsh (DeepSeek Harness), omp, OpenCode, Cursor, Kimi Code, ZCode, and Codex
- Agent Plugin packaging: one-command install; portable across any Agent Plugins v1.0.0 client
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 26
- MCP servers
- 0
- Stars
- 69
- License
- MIT
- Repo created
- 2026-03-06
- Last pushed
- 2026-11-13
- Publisher type
- User
- Version
- 4.5.2
Links
Skills · 26
- grill-me
- Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
- mstar-artifacts
- Morning Star plan harness artifacts: `{PLAN_DIR}` main plans and durable review summaries, `{SDD_DIR}/review/` ephemeral QC/QA bundles, `{KNOWLEDGE_DIR}` / `{ITERATION_DIR}` indexes, plus `{HARNESS_DIR}/status.json` (v2 root register) / `{WORKFLOW_DIR}/<id>/snapshot.json` (plan rows + leases) and…
- mstar-audit
- Morning Star codebase audit: survey any repository and produce prioritized, self-contained improvement plans for the normal Prepare → Execute flow. Strictly read-only on source code. Use when asked to audit or survey a codebase, find improvement opportunities (bugs, security, performance, test gap…
- mstar-branch-worktree
- Morning Star 业务仓 Git 功能分支、worktree 隔离(L1 跨 plan:control worktree + 每 plan feature worktree + `execution_lease`,默认 gitignore 下经 control 绝对路径读写进程产物;L2 同 plan:`references/parallel-writable-pre-dispatch.md`,N 次 invoke ≠ 隔离)、Spec 集成分支、QC/QA 检出对齐(`Review cwd` / `Working branch` / `plan_id` / `Review rang…
- mstar-coding-behavior
- Morning Star 跨角色通用编码行为准则, 任何实现、调试、重构、审查任务动手前必读。约束 Think Before Coding(先读懂再改、显式假设、不静默猜测)、Simplicity First(YAGNI、The Ladder、`simplify:` 标记、最小耐久切片)、Surgical Changes(改动可追溯、Bug 修根因先 grep 所有调用点、不 piggyback)、Debugging(先复现、一步一测、修前写复现测试)、Review Feedback Handling(先核实再改、证据反驳)、Goal-Driven Execution(非平凡逻辑留可运行…
- mstar-conventions
- Morning Star (启明星) harness 计划目录约定, `{HARNESS_DIR}` / `{PLAN_DIR}` / `{SDD_DIR}` / `{ITERATION_DIR}` / `{KNOWLEDGE_DIR}` / `{SPECS_DIR}` / `{WORKFLOW_DIR}` / `{PROJECT_DIR}` 发现与初始化(默认 `.mstar/`,兼容 `.agents/`)、`docs` 与 harness 子树边界、review bundle、未启用 plan 时的工作方式、Spec 集成分支与多 Plan 实现分支(显式 base / merge…
- mstar-design-md
- DESIGN.md design system specification for Morning Star projects. Create, audit, and maintain project-level design tokens (Colors, Typography, Spacing, Elevation, Motion, Shapes, Components, Voice & Content) using Vercel Geist as reference template. Three-level completeness checklist (MVP/Standard/P…
- mstar-design-system
- mstar-dispatch-gates
- Morning Star 派发与委派门禁, 仅 PM 可增派 subagent、`Execute as` 与 `Delegation`、承接方反递归 NEVER 红线、SDD implement 串行派发、**SDD 路径 plan QC 强制 tri-review(N=3)**、inline 单席 QC 例外、Assignment 文案≠派发、未齐不发、**invoke 角色字段必填(漏写=静默 generic 回退=派发未完成)**。`project-manager` 派发时必读;leaf 动手前必读反递归。worktree 见 `mstar-branch-worktree`;SDD…
- mstar-doc-corpus
- mstar-e2e
- mstar-engine-legacy
- Morning Star 条件契约档案(engine-absent fallback)。宿主无 engine 能力(无 `mstar` CLI、无 engine import、engine 约束未激活)时需要被 engine 校验接管的 contract 全文时使用:status v1→v2 字段历史、lease claim 协议全文、各宿主 QC 座次 N=3/N=1 重述、反递归完整清单、Engine-check 样板说明。engine 约束激活(或宿主含 engine 能力)时不加载;运行时 skills 的 engine-check 指针为权威契约。
- mstar-harness-core
- Morning Star (启明星) harness **生命周期 / 授权语义权威与全局入口**, 信息源优先级、最小交付循环、状态机与 Done 权限、Task category 路由(含 quick 禁豁免)、@explore 边界、长任务纪律、核心研发守则、护栏不变量、Morning Star Skill 索引与宿主入口。加载**选择**权威在 **`mstar-roles`**(hub § Load Order 按 Assignment `Skill presets:` 决策;本 skill 不另设全局必读表):PM 与标准路线仍以本 skill 为全局入口;独立直接调用专题时…
- mstar-host
- mstar-iteration
- mstar-knowledge
- mstar-phase-gates
- mstar-pr-loop
- mstar-project-governance
- mstar-prose
- mstar-review-qc
- mstar-roles
- mstar-sdd
- mstar-skill-authoring
- mstar-use-cli
- pm
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
morning-star · mstar · harness · agent · multi-agent · agent-plugin · specification-engineering · harness-engineering · quality-gates · workflow · role-based-workflow · workflow-engine · workflow-enforcement · deterministic-workflow · harness-workflow
Related by publisher and keywords
Amazon requirements discovery and persistent multi-agent delivery with local code intelligence.
Portable multi-agent harness for.agents-based skills and workflows
Frontend implementation, interface design, review, and debugging
Literature search, market research, document extraction, and academic writing
Security scans, source review, and verified remediation
Say it once. Keep it as a file. Nika turns the AI work you repeat into a readable workflow that stays yours: checked before it runs, run with the model you choose, proven afterwards. This package carries the authoring, debugging, operating and migration skills plus the read-only Nika MCP oracle. Requires the nika binary: brew install supernovae-st/tap/nika
[](https://agentpluginsdirectory.com/plugins/morning-star-harness)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.