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 agentmods add skills/ltspace/dowse/skillnpx skills add ltspace/dowse --skill skillgit clone --depth 1 https://github.com/ltspace/dowseWhat 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 | $0.00067 | $0.00795 |
| Opus 5 | $0.00034 | $0.00398 |
| Sonnet 5 | $0.00013 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00080 |
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 3d 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。
三个工具怎么组合用
-
search:先用它定位候选文件。传查询词(支持空格分隔多词 AND 语义、
"短语查询"),可选按扩展名过滤(ext,如"md"、"pdf")。返回按相关度 排序的命中列表,每条带path、score、snippet(命中词用«»标出)、kind(文件类型)。 -
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。 -
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(可选)→ 如果要进一步处理这个文件,直接把
search/preview 返回的 path 喂给文件读取工具(Read 之类)或系统资源管理器,
不需要再转换或拼接,它就是磁盘上的真实绝对路径。
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。
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.
- 3d ago First seen · 45 lines · 67 tokens per session scan A efdae56af5e2
dowse is a skill published in the GitHub repository ltspace/dowse (12 stars, last pushed 3d ago), licensed Apache-2.0. It adds 67 tokens to every session and 795 once invoked, about $0.0003 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
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.
executing-plans
当你有一份书面实现计划需要在单独的会话中执行,并设有审查检查点时使用.
verification-before-completion
在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言.