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 jiggersong/everythingsearch --skill everythingsearch-localgit clone --depth 1 https://github.com/jiggersong/everythingsearchWrote 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/jiggersong/everythingsearch/everythingsearch-local)<a href="https://agentmods.dev/skills/jiggersong/everythingsearch/everythingsearch-local"><img src="https://agentmods.dev/badge/skills/jiggersong/everythingsearch/everythingsearch-local/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/jiggersong/everythingsearch/everythingsearch-local"><img src="https://agentmods.dev/badge/skills/jiggersong/everythingsearch/everythingsearch-local.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 | $0.00104 | $0.03255 |
| Opus 5 | $0.00052 | $0.01628 |
| Sonnet 5 | $0.00021 | $0.00651 |
| Haiku 4.5 | $0.00010 | $0.00326 |
Grade A, and why
everythingsearch-local scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sG "$BASE/api/search" \ Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(["open", filepath], check=True) How it starts
The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EverythingSearch 本地 API(Skills)
本 Skill 指导 Agent 通过 本机已启动的 EverythingSearch HTTP 服务(默认 http://127.0.0.1:8000)完成:
- 直接搜索:
GET /api/search(向量 + 关键词混合,不经过大模型) - 自然语言搜索:
POST /api/search/nl(DashScope 意图识别 → 结构化检索,可触发「精确优先」路径) - 搜索结果智能解读:
POST /api/search/interpret或/api/search/interpret/stream(基于当前结果列表的短总结) - 读文本 / 下载 / 在 Finder 中揭示 等与历史一致的能力
设计细节与 Web 行为见仓库内 docs/NL_SEARCH_AND_WEB_UI.md;完整路由与配置见 docs/PROJECT_MANUAL.md 第 4.6 节。
前置条件
- 用户已在本机运行搜索服务(例如
./scripts/run_app.sh start)。 - 若连接失败,提示用户先启动服务并确认
config.py中的HOST/PORT(多实例安装可查看scripts/.launchd_instance中的APP_PORT)。 - 非本机访问时由用户提供完整服务基址(须带 scheme,例如
http://192.168.1.10:8000)。
BASE="http://127.0.0.1:8000" # 按 config.HOST / config.PORT 或用户给出的 URL 调整
智能能力对 DashScope API Key 的依赖
GET /api/search:不调用生成式模型;仅需本地向量库已构建(嵌入阶段仍需要 Key 建索引)。POST /api/search/nl、/api/search/interpret*:服务端需在config.py配置MY_API_KEY。未配置时这些接口会返回业务错误(如MISSING_API_KEY),Agent 应退化为GET /api/search完成检索。- 意图识别与解读会访问外网模型服务;默认限流见配置
RATE_LIMIT_NL_PER_MIN、RATE_LIMIT_INTERPRET_PER_MIN(常见默认各约每分钟每 IP 10 次,以everythingsearch/infra/settings.py为准)。
1. 直接搜索(混合检索,无大模型)
语义与关键词混合检索;结果中 preview 为围绕命中的短片段。
RESULT_JSON="$(mktemp /tmp/essearch.XXXXXX.json)"
printf '%s\n' "$RESULT_JSON"
curl -sG "$BASE/api/search" \
--data-urlencode "q=你的关键词或短句" \
--data-urlencode "source=all" \
--data-urlencode "limit=30" \
-o "$RESULT_JSON"
可选查询参数(与校验逻辑一致时):date_field(mtime|ctime)、date_from、date_to、limit(1~200)。
source:all|file|mweb(若实例关闭 MWeb,勿用mweb)。- 注意:
GET /api/search没有exact_focus参数;「精确优先」检索仅由下面的 NL 路径在解析出exact_focus后触发。
响应 JSON:results[] 含 filename, filepath, preview, relevance, tag(如「语义匹配」「精确匹配」), mtime, source_type 等;另有 query 字段。
2. 自然语言搜索(意图 → 检索)
将用户整句自然语言交给模型解析为结构化检索参数(核心检索词 slots.q、来源、时间、match_mode 等),再执行与 Web 相同的搜索管线。
RESULT_JSON="$(mktemp /tmp/essearch-nl.XXXXXX.json)"
printf '%s\n' "$RESULT_JSON"
curl -s -X POST "$BASE/api/search/nl" \
-H "Content-Type: application/json" \
-d '{
"message": "帮我找去年关于预算的 excel",
"sidebar_source": "all",
"date_field": "mtime",
"date_from": null,
"date_to": null,
"limit": 30
}' \
-o "$RESULT_JSON"
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 First seen · 245 lines · 104 tokens per session scan A 2e16c29c68fa
everythingsearch-local is a skill published in the GitHub repository jiggersong/everythingsearch (5 stars, last pushed 23d ago), licensed MIT. It adds 104 tokens to every session and 3,255 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…