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/cloud99277/kitclaw/knowledge-searchnpx skills add cloud99277/KitClaw --skill knowledge-searchgit clone --depth 1 https://github.com/cloud99277/KitClawWhat 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 | $0.00083 | $0.01473 |
| Opus 5 | $0.00042 | $0.00737 |
| Sonnet 5 | $0.00017 | $0.00295 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
knowledge-search 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 2d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
knowledge-search
本地 Markdown 知识库语义检索 Skill，基于 LanceDB 向量 + Tantivy FTS 混合搜索。
快速开始
按场景搜索（推荐）
# 编码场景：精确查架构决策（top 3, scope=dev）
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "Embedding 模型选型" --preset coding
# 审查场景：对比历史调研（top 5, scope=dev）
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "RAG 技术选型" --preset audit
# 提问场景：广泛搜索回答用户（top 10）
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "Git 同步策略" --preset qa
# 快速模式：FTS-only，跳过 Embedding 加载（<1s）
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "pre-commit" --preset fast
高级参数
# 自定义搜索模式和数量
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "查询" \
--mode hybrid \
--top 5 \
--db-path ~/.lancedb/knowledge \
--scope dev \
--tags architecture
# 按时间过滤
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "查询" \
--after 2026-03-01
# 按作者过滤
bash ~/.ai-skills/knowledge-search/scripts/knowledge-search.sh "查询" \
--author agent
搜索 Preset 配置
| preset | 搜索模式 | 数量 | scope | 适用场景 |
|---|---|---|---|---|
coding |
hybrid | 3 | dev | 编码时查架构决策、技术选型 |
audit |
hybrid | 5 | dev | 审查文档时对比历史调研 |
qa |
hybrid | 10 | （不限） | 回答用户知识提问 |
fast |
fts | 5 | （不限） | 快速关键词匹配，跳过模型加载 |
fastpreset 使用 FTS（全文检索），不加载 Embedding 模型，延迟 <1秒。 其他 preset 使用 hybrid（向量 + FTS + RRF 融合），首次加载模型约 3-5 秒。
输出格式
所有输出为 JSON 格式，遵循以下 Schema：
{
"schema_version": "1.0",
"query": "搜索文本",
"mode": "hybrid",
"preset": "coding",
"total_results": 3,
"results": [
{
"chunk_id": "c12b2f551397",
"text": "匹配的文本内容...",
"score": 0.85,
"source_file": "docs/RESEARCH-RAG-TECH.md",
"heading_path": ["# RAG 技术调研", "## 向量数据库选型"],
"line_range": "L45-L78",
"metadata": {
"title": "RAG 技术调研",
"scope": "dev",
"tags": "rag,architecture"
}
}
]
}
字段说明
| 字段 | 类型 | 说明 |
|---|---|---|
schema_version |
string | 输出格式版本，当前 "1.0" |
query |
string | 原始查询文本 |
mode |
string | 实际使用的搜索模式 |
preset |
string | 使用的 preset 名称（如有） |
total_results |
int | 返回结果数 |
results[].chunk_id |
string | 文本块唯一 ID |
results[].text |
string | 匹配的文本内容 |
results[].score |
float | 相关度评分（0-1，越高越相关） |
results[].source_file |
string | 来源文件路径 |
results[].heading_path |
list | 标题层级路径 |
results[].line_range |
string | 行号范围（如 "L45-L78"） |
results[].metadata |
object | 文件元数据（title, scope, tags, author, date） |
What ships with it
3 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.
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.
- 2d ago First seen · 152 lines · 83 tokens per session scan A 7cb2e973d725
knowledge-search is a skill published in the GitHub repository cloud99277/KitClaw (5 stars, last pushed 4mo ago), licensed MIT. It adds 83 tokens to every session and 1,473 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…