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 ltspace/dowse --skill skillgit clone --depth 1 https://github.com/ltspace/dowseWrote 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/ltspace/dowse/skill)<a href="https://agentmods.dev/skills/ltspace/dowse/skill"><img src="https://agentmods.dev/badge/skills/ltspace/dowse/skill/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/ltspace/dowse/skill"><img src="https://agentmods.dev/badge/skills/ltspace/dowse/skill.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 | $0.00067 | $0.00915 |
| Opus 5.5 | $0.00027 | $0.00366 |
| Sonnet 5.5 | $0.00013 | $0.00183 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
dowse 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 1mo 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
dowse：本地全盘搜索
dowse 是一个常驻 Windows 的本地全文搜索索引（tantivy + jieba 分词），浮窗应用 负责建索引、增量更新；这个 MCP server 是它的只读查询接口，不提供任何会修改 索引的工具。用户问"我硬盘上关于 XXX 的笔记/文档/配置在哪"这类问题时，优先用 这里的工具而不是让 agent 自己去遍历文件系统或调用 grep 类工具。dowse 的索引 覆盖了用户机器上所有已收录的目录，一次查询就能跨全盘命中，比现场扫描快得多、 也不会漏掉不在当前工作目录下的文件。
四个工具怎么组合用
-
search：先用它定位候选文件。查询支持多词 AND、
"短语"、大写OR、NOT/-词，以及path:、mtime:、size:操作符；还可按多个扩展名过滤、 按相关度/修改时间/体积排序，并用limit/offset翻页。返回中的total_hits是总命中数，path是后续工具使用的精确路径。 -
preview：从 search 结果里挑一条，把它的
path和当时用的query传 给 preview，拿到一段长得多的上下文（约 1500 字，也带«»高亮），外加 文件大小、修改时间。search 的 snippet 只有 160 字左右，判断"是不是这篇" 经常不够，需要看更多上下文时用 preview，不用自己去读整个文件。 -
read_file_chunk：preview 仍不够时，用 search 返回的
path分页读取已索引 正文。默认 4000 字，单页最多 8000 字；如果next_offset_chars非空，把它作为 下一次的offset_chars。内容来自索引快照，不要把它描述为刚从原文件读取。 -
index_status：不需要参数。想知道索引里有多少文档、覆盖了哪些根目录、 索引落盘多大、最近一次更新是什么时候，调这个。比如 search 一直没命中时， 可以先查一下 index_status 确认索引没坏、确实收录过东西。
典型顺序：search → preview → read_file_chunk（仅在需要更多正文时）。如果要用
别的工具进一步处理原文件，直接使用返回的 path，不需要转换或拼接。
用不到的时候
- 索引里没有的目录（用户从没让 dowse-app 收录过）搜不到，这不是 bug，是
dowse 的设计边界，它只覆盖用户主动收录的目录。index_status 的
roots字段能看到当前覆盖了哪些目录。 - 索引不存在或损坏时，工具会返回结构化错误加一句建库指引（
dowse index <目录>）， 不会崩溃；看到这个提示时告诉用户去 dowse-app 浮窗或命令行建一次索引， 不要自己瞎猜路径重试。 - 这里没有任何写操作：建索引、重建索引、增删收录目录都不在这个工具集里，
需要用户自己在 dowse-app 浮窗或
dowse index命令行里做。 - read_file_chunk 只能返回已经写入索引的正文，不是通用文件读取器；路径不在索引里
会返回结构化的
path_not_found。
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.
- 1mo ago Changed · +5 lines 68d215fc87de
- 1mo ago First seen · 45 lines · 67 tokens per session scan A efdae56af5e2
dowse is a skill published in the GitHub repository ltspace/dowse (35 stars, last pushed 6d ago), licensed Apache-2.0. It adds 67 tokens to every session and 915 once invoked, about $0.0003 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
patent-map
A tool for making a visual map of stored patent case notes in an Obsidian vault. Obsidian is a note-taking application that stores linked text files.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
seedance-vocab-zh
This skill should be used when the user asks for Chinese Seedance 2.0 prompt wording, Mandarin cinematic vocabulary, Chinese prompt compression, or translation of camera, lighting, action, VFX, audio, and production terms into Chinese.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
skill-contract-reviewer
Validate an Agent Skill package and choose the right instruction, capability, or lifecycle primitive before implementation.