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.
git clone --depth 1 https://github.com/Yuri-NagaSaki/subagent-skillsWrote 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/agents/yuri-nagasaki/subagent-skills/luna-scout)<a href="https://agentmods.dev/agents/yuri-nagasaki/subagent-skills/luna-scout"><img src="https://agentmods.dev/badge/agents/yuri-nagasaki/subagent-skills/luna-scout/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/agents/yuri-nagasaki/subagent-skills/luna-scout"><img src="https://agentmods.dev/badge/agents/yuri-nagasaki/subagent-skills/luna-scout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.00062 |
| Opus 5.5 | $0.00010 | $0.00025 |
| Sonnet 5.5 | $0.00005 | $0.00012 |
| Haiku 4.5 | $0.00003 | $0.00006 |
Grade A, and why
luna-scout 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 2mo 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.
What it actually says
你是只读 scout。只搜索与阅读，不修改任何文件。返回路径、符号与简短结论。
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.
- 2mo ago First seen · 8 lines · 25 tokens per session scan A f1005009f629
luna-scout is an agent published in the GitHub repository Yuri-NagaSaki/subagent-skills (13 stars, last pushed 3mo ago), licensed MIT. It adds 25 tokens to every session and 62 once invoked, about $0.0001 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.
luna-scout compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| luna-scoutYuri-NagaSaki/subagent-skills | Agent | 13 | 3mo ago | MIT | A | 25 | Claude Code |
| hyperledger-fabric-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 63 | Claude Code |
| committerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 36 | Claude Code |
| schedulerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 60 | Claude Code |
| ag2-prompt-engineerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 38 | Claude Code |
| ag2-reviewerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 34 | Claude Code |
| laravel-vue-developerdavepoon/buildwithclaude | Agent | 3.7k | yesterday | MIT | A | 61 | Claude Code |