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-engine-legacygit 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-engine-legacy)<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-engine-legacy"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-engine-legacy/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-engine-legacy"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-engine-legacy.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 | $0.00142 | $0.01124 |
| Opus 5 | $0.00071 | $0.00562 |
| Sonnet 5 | $0.00028 | $0.00225 |
| Haiku 4.5 | $0.00014 | $0.00112 |
Grade A, and why
mstar-engine-legacy 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mstar-engine-legacy（条件契约档案 / Engine-absent fallback）
Load Order
- 先 Read
mstar-harness-core（SKILL.md；冲突时以 core 为准）。 - 条件加载：仅当宿主无 engine 能力时读取本 skill 及其 references —— 无
mstarCLI、无 engine import、engine 约束未激活。engine 约束激活（或宿主含 engine 能力）时不加载：此时运行时 skills 的 engine-check 指针 + 短契约文本为权威（见 core 索引行）。 - 本 skill 是单一条件归档：承接因 engine 校验而从运行时 skills 中移除的 contract 全文，engine-absent 宿主在此找回完整文本。
Scope
- 归档被承接的完整契约散文（Task 2 displaced prose 的单一收容处）：
status.jsonv1→v2 字段历史表（字段、severity、lifecycle、jq/flock 示例）- lease claim 协议全文（claim-before-InProgress、hold/release/override、integration merge、orphan recovery、waiver）
- 各宿主 QC 座次 N=3/N=1 重述（omp / opencode / cursor / codex / kimi / zcode / dsh）
- 反递归完整清单（leaf executor checklist、红线、NEVER 规则）
- Engine-check 样板含义（运行时 skills 中
Engine check (when available)blockquote 的语义与 fallback 规则）
- 运行时 skills 只保留短指针 + engine-check 命令；完整全文一律在本 skill 的
references/中（避免全仓重复）。
Workflow
- 确认触发条件：宿主无 engine（无 CLI / import；约束未激活）。满足才继续。
- 按需打开对应 reference（见下表），把其中的完整契约文本作为 fallback 应用。
- engine 恢复后回到运行时 skills 的指针契约，停止使用本文件作为权威。
| 需要 | 打开 |
|---|---|
| status 字段 / severity / lifecycle / 迁移 / jq-flock 示例 | references/status-field-history.md |
| lease claim 协议全文（claim / hold / merge / orphan / waiver） | references/lease-protocol.md |
| 各宿主 QC 座次 N=3/N=1 重述 | references/qc-seat-n-restatements.md |
| 反递归完整清单（leaf checklist + 红线） | references/anti-recursion-checklists.md |
| Engine-check 样板含义与 fallback 规则 | references/engine-check-boilerplate.md |
Decision Rules
- 不加载条件：engine 约束激活，或宿主含 engine 能力（
mstarCLI / engine import 可用）→ 本 skill 不加载。 - 归档唯一性：完整契约文本只存在于本文件；不得同时在运行时 skills 重复维护全文（运行时只放指针 + engine-check）。
- 权威性：engine-absent 时，本文件的完整文本是行为权威；engine-present 时，运行时 skills + engine 校验是权威，本文件不是。
- 不改契约语义：承接文本必须逐字保留（字段名、severity 枚举、lease 规则、N 规则、反递归清单）；只做整理与归档，不重写规则。
Evidence
- 正确结果 = references 中的完整文本可独立支撑 engine-absent 宿主操作；
bun run validation:drift绿（skill corpus lint 通过）；mstar skill lint skills/mstar-engine-legacy绿。 - 回归 = grep 验证运行时 skills 已不再携带被承接的全文（原全文位置只剩指针 / engine-check）。
What ships with it
5 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 · 54 lines · 142 tokens per session scan A af67f0f4dfcb
mstar-engine-legacy is a skill published in the GitHub repository btspoony/mstar-harness (58 stars, last pushed today), licensed MIT. It adds 142 tokens to every session and 1,124 once invoked, about $0.0007 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.