Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add btspoony/mstar-harness --skill mstar-phase-gatesgit clone --depth 1 https://github.com/btspoony/mstar-harnessWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/btspoony/mstar-harness/mstar-phase-gates)<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-phase-gates"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-phase-gates/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-phase-gates"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-phase-gates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00183 | $0.02838 |
| Opus 5 | $0.00092 | $0.01419 |
| Sonnet 5 | $0.00037 | $0.00568 |
| Haiku 4.5 | $0.00018 | $0.00284 |
Grade A, and why
mstar-phase-gates scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load order(必读顺序)
首次 Read 本 skill 前:必须先 Read mstar-harness-core(SKILL.md)。 {PLAN_DIR} / plan 文件落盘见 mstar-conventions。冲突时 以 mstar-harness-core 为准。
Spec-Driven 双阶段门禁(非热修强制)
A. Prepare:specify → clarify → plan
specify— 问题陈述、用户价值、范围/非目标、DoD 草案。clarify— 关键歧义清单与结论;高影响歧义必须收敛,否则Blocked。- 意图核对(Intent gate):区分用户字面表述与待解决的真正问题;手段与目标混淆须在此收敛。
- 结构化澄清:宿主提供
question工具时优先使用;否则用结构化正文选项。宿主细节在各自的mstar-hostskill。 clarify核心纪律(Prepare):对 plan/方案的每个方面持续核对,直到与用户达成共享理解;沿设计决策树逐枝下行,一次只收敛一个决策点及其依赖,再进入下一枝。- 能查库则查库:若问题可通过探索代码库(实现、配置、
{SPECS_DIR}、{KNOWLEDGE_DIR}、{ITERATION_DIR}等)得到答案,先探索、不向用户提问。 - 每问带推荐:每个仍需用户确认的问题,须给出推荐答案(及简短理由),便于快速对齐。
- 收口摘要:
clarify结束前列出:已决事项、仍 open 的假设、对plan的约束。
- 能查库则查库:若问题可通过探索代码库(实现、配置、
plan— 技术方案、长期目标状态、模块边界/接口契约、风险与回滚点、验证计划。- 意图门禁:锁 plan 前须能书面写清真实目标 / 成功判据 / 非目标三项;否则 Prepare 未通过。
- 长期方案优先:默认先设计目标状态,再裁剪本轮可交付切片;不得以“临时方案 / 混合方案 / 以后再说”替代目标设计。
- Durable Roadmap Gate:若本轮只做部分范围,plan 必须写明 roadmap(批次、依赖、暂缓项、owner/触发条件、最终完成定义)。只有一句“后续再做 / next plan”视为未通过 plan gate。
B. Execute:plan(locked) → tasks → implement
plan(locked)— 冻结基线;实现中出现新约束时先回写 plan 再继续。tasks— 含依赖顺序、并行标记、完成判据;每任务可追踪到 plan、roadmap 批次与验收标准。- 并行标签:≥2 条实现轨同时分派 →
Dispatch mode: parallel independent tracks;同仓可写并发 →Worktree isolation: required(清单mstar-branch-worktree→references/parallel-writable-pre-dispatch.md)。
- 并行标签:≥2 条实现轨同时分派 →
implement— 按 tasks 顺序执行;多 task plan 默认Execution mode: sdd(mstar-sdd);hotfix 可inline。完成进入InReview;遵循mstar-coding-behavior。
可验证编辑与上下文纪律
- 读后再改:修改文件前以磁盘内容为准重读(
Read/等价工具)。 - 小步应用:Patch 失败禁止在同一过时锚点连试;重读、缩小变更单元或拆步。
- 多文件改动:逐项核对路径与引用,避免未验证的批量替换。
Hotfix 例外
压缩路径与事后补记见下文 § Hotfix 例外(Playbook 末尾)。
Phase Gate Playbook
执行动作与最小产物见上文 § Spec-Driven 双阶段门禁。本节仅 Playbook 补充(不重复 Prepare/Execute 长文)。
Execute 补充(Playbook 专有)
plan locked- 最小动作:在 plan 或 notes 记录当前锁定版本(日期或 hash)。
- Plan 质量门(新 plan / 大改):无 placeholder(
...、TBD、etc.);含 Global Constraints 与 per-task Interfaces;PM self-review 三问(每 task 可独立验证?依赖顺序清晰?无隐含假设?)— 见mstar-artifacts/templates/plan.main.md+mstar-artifacts/references/plan-quality-bar.md(自包含/验证门/STOP 条件/drift check/done criteria)。
implement- 最小产物:实现 diff、自检证据、回报与 handoff;行为准则 →
mstar-coding-behavior;编辑纪律 → 上文「可验证编辑与上下文纪律」。 - 知识库 / 迭代 compass:默认开工前扫
{KNOWLEDGE_DIR}/README.md索引(若存在)并阅读与当轮相关的 Active 行(即使 metadata 无 knowledge 链接);若plans[].metadata登记了primary_spec/spec_refs/iteration_compass/iteration_refs,所链接文档仍须阅读;两类阅读均须在回报中说明已对齐 →mstar-conventions·mstar-artifacts/references/knowledge-and-designs.md。
- 最小产物:实现 diff、自检证据、回报与 handoff;行为准则 →
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 119 lines · 183 tokens per session scan A 16829134dded
mstar-phase-gates is a skill published in the GitHub repository btspoony/mstar-harness (57 stars, last pushed today), licensed MIT. It adds 183 tokens to every session and 2,838 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
comet-native
A workflow for managing Native changes in Comet, where requirements, progress, and acceptance results are saved in project files. It uses the Comet command-line runtime to move through defined work stages.
comet-build
A Comet workflow step for turning an approved design into an implementation plan and completed code changes. Comet is the project workflow system described by the add-on.
comet-classic
A Chinese-language workflow guide for starting or resuming a structured software change using OpenSpec and Superpowers.
comet-open
A guide for starting an OpenSpec change: a tracked software task with proposal, design, task, and state files. It also covers choosing or restoring the correct project workspace and output language.
comet-build
Comet Phase 3: Plan and Build. Invoke with /comet-build. Create plans and select execution method (subagent or direct) for implementation.
subagent-driven-development
Use when executing implementation plans with independent tasks in the current session.