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-hostgit 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-host)<a href="https://agentmods.dev/skills/btspoony/mstar-harness/mstar-host"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-host/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-host"><img src="https://agentmods.dev/badge/skills/btspoony/mstar-harness/mstar-host.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 | $0.00055 | $0.04031 |
| Opus 5.5 | $0.00022 | $0.01612 |
| Sonnet 5.5 | $0.00011 | $0.00806 |
| Haiku 4.5 | $0.00006 | $0.00403 |
Grade A, and why
mstar-host 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 9d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Morning Star Host Adapter
Host-specific capabilities and entry behavior for Morning Star. Process gates and invariants stay in mstar-harness-core and topic mstar-* skills.
Load order
本 skill 总是在 mstar-harness-core 之后加载（先 Read mstar-harness-core SKILL.md；宿主注入项目 AGENTS.md 也不跳过，见下 ## First action）。本 skill 只适配宿主入口 / 检测 / 计划 UX；状态机与门禁以 mstar-harness-core 为准。
First action
Read mstar-harness-core before this skill (even when the host injects project AGENTS.md).
Default path
- Read
mstar-harness-core - Read
mstar-host(this skill) and detect host below - Read
references/<host>.mdfor the active host - Load role via
mstar-roles - Execute with evidence-first completion checks
Load topic skills on demand per mstar-roles (do not read every mstar-* skill by default). Cursor routing-eval (.cursor/skills/mstar-routing-eval/) is regression tooling only — not part of runtime load order.
Detect active host
Detect from session tool shapes and available commands — not from plugin markers on disk. The *-plugin/plugin.json files cannot identify the host: they all coexist in this harness source repo and in any multi-host install.
| Signal | Host | Next read |
|---|---|---|
subagent_type param on the Task tool (plus CreatePlan/SwitchMode when Plan mode is active) |
cursor |
references/cursor.md; Plan mode also references/cursor-plan-mode-bridge.md |
question tool, or task tool with subagent (singular) — no tasks[] batch |
opencode |
references/opencode.md |
task tool with agent / tasks[] batch, ask, hub (omp also exposes /goal; goal rule is host-agnostic per below) |
omp |
references/omp.md; Plan mode also references/omp-plan-mode-bridge.md |
subagent tool (dsh's model-facing delegation tool — @deepseek-ai/dsh-tool-subagent default toolName), spawn_teammate / team_task_create (dsh Agent Teams tools — @deepseek-ai/dsh-experimental-tool-agent-team) |
dsh |
references/dsh.md |
Agent / AskUserQuestion / EnterPlanMode + AgentSwarm (Kimi-only) |
kimi |
references/kimi.md; Plan mode also references/kimi-plan-mode-bridge.md |
Agent / AskUserQuestion / EnterPlanMode / TodoWrite, no AgentSwarm |
zcode |
references/zcode.md; Plan mode also references/zcode-plan-mode-bridge.md |
/plan, /goal slash commands; Goal tools; functions.* / codex_app.* tool namespaces; tool_search; Browser plugin tools |
codex |
references/codex.md; Plan mode also references/_shared/plan-mode-bridge-core.md |
| Still ambiguous | - | Read sections in cursor.md, opencode.md, codex.md, kimi.md, zcode.md, omp.md, and dsh.md that match tools you have; mstar-harness-core wins on conflict |
What ships with it
16 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.
- references/_shared/host-role-binding-core.md 2.9 KB
- references/_shared/plan-mode-bridge-core.md 11 KB
- references/codex.md 9.3 KB
- references/cursor-plan-mode-bridge.md 10 KB
- references/cursor.md 14 KB
- references/dsh-agent-teams.md 16 KB
- references/dsh-workflow-scripts.md 32 KB
- references/dsh.md 77 KB
- references/kimi-plan-mode-bridge.md 3.5 KB
- references/kimi.md 11 KB
- references/omp-plan-mode-bridge.md 2.9 KB
- references/omp.md 55 KB
- references/opencode.md 14 KB
- references/parallel-dispatch.md 6.1 KB
- references/zcode-plan-mode-bridge.md 3.4 KB
- references/zcode.md 16 KB
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.
- 9d ago Changed · +2 lines 680706543edc
- 13d ago Changed 9561f1d25f19
- 16d ago Changed · -44 tokens per session 4d2688fa296f
- 17d ago Changed a49a0d724001
- 18d ago Changed d43720f5ea95
- 27d ago Changed 72cc245a9e97
- 1mo ago Changed · -1 lines 57b301d886ea
- 1mo ago Changed e2b4bd37ffd8
- 1mo ago Changed · +2 lines ae67aff052d5
- 1mo ago First seen · 139 lines · 99 tokens per session scan A fea027f6e478
mstar-host is a skill published in the GitHub repository btspoony/mstar-harness (68 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 4,031 once invoked, about $0.0002 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.
mstar-host compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mstar-hostbtspoony/mstar-harness | Skill | 68 | 2d ago | MIT | A | 55 | Claude Code |
| comet-openrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 33 | Codex |
| subagent-driven-developmentrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 17 | Claude Code, Codex |
| comet-buildrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 36 | Claude Code, Codex |
| cometrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 44 | Claude Code, Codex |
| comet-classicrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 48 | Codex |
| comet-designrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 29 | Claude Code, Codex |