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-routing-evalgit 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-routing-eval)<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-routing-eval"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-routing-eval/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-routing-eval"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-routing-eval.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 | $0.00129 | $0.05177 |
| Opus 5.5 | $0.00052 | $0.02071 |
| Sonnet 5.5 | $0.00026 | $0.01035 |
| Haiku 4.5 | $0.00013 | $0.00518 |
Grade A, and why
mstar-routing-eval 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 25d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintainer scope（维护专用 · Cursor）
- 不是 runtime pack：日常
specify → implement → QC不要求 Read 本 skill；已从skills/mstar-*运行时包中拆出，避免与「每轮必读」混淆。 - Canonical 位置：本仓库内 仅此目录（
.cursor/skills/mstar-routing-eval/）为正文 +assets/SSOT；不再维护skills/mstar-routing-eval/副本。 - 谁在读：
@prompt-engineer改规则前；维护者改project-manager/ harness 门禁后跑回归；repo-maintenance清单涉及路由时。
Load order（必读顺序）
在同一会话或任务中首次 Read 本 skill 时：必须先 Read mstar-harness-core skill（SKILL.md，以及评估路由与门禁时需要的 mstar-harness-core/references/）。 本 skill 的 routing-evals.json 场景校验的是对 harness 的遵守情况；若未建立 harness 上下文，评估易与真实门禁脱节。冲突时 以 mstar-harness-core 为准。
摘要：mstar-harness-core — 期望路由与 phase gate；本 skill — 场景集、Routing Eval Report 模板与回归方法。
Morning Star Routing & Evaluation Harness
1. PM 路由评估
本节用于验证 @project-manager 是否将任务路由到正确的 agent 和门禁。
输入
- 场景集：本 skill 的
assets/routing-evals.json - 路由策略来源：
mstar-rolesskill 的project-manager角色 - 全局约束：
mstar-harness-coreskill（含 harness 不变量与 skill 索引）
评估方法
对每个场景：
- 将实际路由与
expected_route进行比对。 - 检查所需产出是否已规划并最终产出。
- 验证没有
hard_fail_if条件被违反。 - 验证
Context Loaded已声明且包含必要文件。 - 验证 Assignment 的语言契约：字段名英文、任务正文可中文、执行产出/报告英文（除非用户明确要求其他语言）。
- 记录路由质量和缺失的证据。
Authority-aware fixture interpretation：未显式标注文件路由的断言按 ACTIVE 主线判定：integration_merge_lease 是 workflow 级串行合并 exclusion 的逻辑名称，经公共 workflow view 读取（per-plan execution lease 已移除，fixture 不得要求 per-row lease/claim 断言）；协调写入经公共动词的事务 + execution-token CAS。仅显式 pre-activation / engine-absent 场景保留 snapshot + same-host 文件锁语义。control root 是主 checkout 的路径定位，不要求发明 ACTIVE control_worktree_path 列；branch anchors 与 integration_worktree_path 经执行域 workflow view 读取。open findings 始终为 store linked issues，residuals.json 只作迁移历史。措辞 SSOT → mstar-artifacts、mstar-branch-worktree L1、mstar-dispatch-gates 与 mstar-iteration/references/phase-2-worktree-lease.md §2.0 / Coordination transactions。
评估执行步骤（1-2-3）
- 准备输入：加载当前
assets/routing-evals.json、project-manager.md、mstar-harness-core（含 references）。 - 逐案判定：按
expected_route/must_have_artifacts/hard_fail_if打分并记录证据。 - 输出报告：按下文
Routing Eval Report模板汇总（含phase_gate_compliance_rate）。
What ships with it
1 file 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.
- 25d ago Changed · -2 lines efae3d4213fe
- 26d ago Changed · +2 lines 5015497e80cc
- 28d ago Changed · +1 lines 4e2ecb75d17e
- 29d ago Changed · +2 lines e21cd4f611ee
- 1mo ago Changed · +5 lines 96d1554b2430
- 1mo ago Changed 6fd7bafcbbde
- 1mo ago Changed 2832f5836315
- 1mo ago Changed · +6 lines 14ea3b954d48
- 1mo ago Changed · +7 lines f15bcc7a846b
- 2mo ago First seen · 232 lines · 129 tokens per session scan A ba8858dc1e25
mstar-routing-eval is a skill published in the GitHub repository btspoony/mstar-harness (67 stars, last pushed yesterday), licensed MIT. It adds 129 tokens to every session and 5,177 once invoked, about $0.0005 per session on Opus 5.5. 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
grill-test
An end-to-end test workflow that runs a sequence of planning and implementation skills through real user confirmations and tests. It covers grilling an idea, writing a specification, creating tickets, implementing them, and reviewing the result.
comet-verify
A workflow for verifying a Comet change after its coding tasks are complete. Comet is a tool that tracks structured software changes through stages.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
implement
Implement a piece of work based on a spec or set of tickets.