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-skill-authoringgit 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-skill-authoring)<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-skill-authoring"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-skill-authoring/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-skill-authoring"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-skill-authoring.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 | $0.00096 | $0.02395 |
| Opus 5 | $0.00048 | $0.01197 |
| Sonnet 5 | $0.00019 | $0.00479 |
| Haiku 4.5 | $0.00010 | $0.00239 |
Grade A, and why
mstar-skill-authoring 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 11d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Authoring
本 skill 约束如何编写、审查与验证 任意 agent skill（SKILL.md）。面向 skill 工作，不是普通应用实现。
Load Order
在本 harness 仓库内工作时：先 Read mstar-harness-core（加载 / 冲突裁决）；仓库维护另遵根目录 AGENTS.md。
在其它仓库 / 宿主上使用本 skill 时：按当地入口文档加载；本文件的原则与门控仍然适用。
改现有 skill 时：读完被改 skill 及其 SSOT 引用；禁止仅为文风重写相邻 skill。
详细 writer 流程与输出模板 → references/skillsbench-authoring.md（需要完整循环时再读）。
Workflow
主链：按「Frontmatter Contract」先定触发契约（原则 3）→ 按「Body 必须回答的 5 问」写默认紧凑 body（原则 2）→ 变体细节按「Progressive Disclosure」进 references/ / templates/ / scripts/ → 行为塑形改动按「验证门控（Evidence，原则 4 + 6）」留 paired 证据 → 按「Review Template」自审并完成「完成时主动说明」三问。
6 条作者原则（Decision Rules，必须遵守）
来源：SkillsBench 大规模实验。违反任一都会降低 agent 性能。
| # | 原则 | 强制动作 |
|---|---|---|
| 1 | 专家流程优先 | 先提取真实操作步骤、决策标准、约束、API 坑与失败恢复；模型只做编辑器。禁止把一键生成稿当最终版。 |
| 2 | 紧凑程序性 | body 只答 5 问（见下）；详例 / 长文档进 references/，按需加载。过长 body 几乎无提升甚至负提升。 |
| 3 | 路由最小化 | 任务真正需要时才加载；目标 1–3 个 skill。description 必须具体到可精准匹配，避免无关激活。 |
| 4 | 按 model+harness 实测 | 文件可移植 ≠ 行为可移植。在实际使用的模型与宿主（omp / Cursor / Codex / Claude Code 等）分别验证触发、执行、token、回归。 |
| 5 | 只补模型缺口 | 编码内部约定、受监管流程、脆弱 API、专业判断、反复失败模式。不写模型已会的通用知识。 |
| 6 | 每次改动=受控实验 | 必须有 paired 证据（with vs without，或 before/after + 可观察标准）。held-out / 压力场景未提升则拒绝合入。禁止“感觉更好”。 |
Body 必须回答的 5 问
合格 SKILL.md 只清晰回答：
- 何时加载？（触发 / 排除）
- 按什么顺序与关键决策点执行？
- 哪些约束 / 不变量绝不可违反？
- 正确结果长什么样？（成功标准 / 证据）
- 主路径不够时打开哪些额外资源？
答不进这 5 问的内容 → 删或移到 references/。
运行时别名（runtime alias map）
已发布的 mstar-* 专题 skill 允许运行时模式（lintFiveQuestion(body, "runtime")）用锁定别名表回答同一问题（引擎常量 RUNTIME_HEADING_ALIASES）：
| 问题 | 运行时别名（标题子串，大小写不敏感） |
|---|---|
| Workflow | process、playbook |
| Decision Rules | hard rules、core rules、rule、gate、not to do、red flags、反模式、红线、规则、门禁 |
| Evidence | output format、证据 |
| References | dependencies、关系 |
- 别名表是锁定表：改表必须同步引擎回归测试与 corpus。
- 新写 / greenfield skill（authoring / strict）仍要求 canonical 标题；运行时别名只豁免已发布专题 skill 的机械 lint，不豁免语义——别名标题必须真实回答对应问题，正文不得因别名而缩水。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 182 lines · 96 tokens per session scan A b39850249701
mstar-skill-authoring is a skill published in the GitHub repository btspoony/mstar-harness (58 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,395 once invoked, about $0.0005 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.