Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/iflow-ai/iflow-skillsnpx agentmods add skills/iflow-ai/iflow-skills/searchWrote 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/iflow-ai/iflow-skills/search)<a href="https://agentmods.dev/skills/iflow-ai/iflow-skills/search"><img src="https://agentmods.dev/badge/skills/iflow-ai/iflow-skills/search/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/iflow-ai/iflow-skills/search"><img src="https://agentmods.dev/badge/skills/iflow-ai/iflow-skills/search.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 | $0.00039 | $0.01807 |
| Opus 5 | $0.00019 | $0.00903 |
| Sonnet 5 | $0.00008 | $0.00361 |
| Haiku 4.5 | $0.00004 | $0.00181 |
Grade A, and why
happy-notes-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 11d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
联网搜索（Web Search）
前置条件：参见根目录
../SKILL.md了解凭证配置和iflow_api()辅助函数。
通过 iflow API 进行联网搜索（网页和学术论文），支持快速搜索和深度研究两种模式。搜索结果默认导入知识库并可生成报告等产出物，也可通过 --search-only（只看结果）或 --no-generate（只导入不生成）控制行为。
完整数据结构和接口参数详见 references/api.md 第 7 节。
何时使用 Pipeline 6 vs Agent 自身搜索
Pipeline 6 是面向知识库的搜索能力：搜索外部内容后导入知识库、整理、生成产出物。它不是通用搜索引擎。
| 用户意图 | 正确处理方式 | 原因 |
|---|---|---|
| "搜一下XX的论文，整理成报告" | Pipeline 6 | 需要导入知识库 + 生成产出物 |
| "深度研究一下XX" | Pipeline 6 (DEEP_RESEARCH) |
需要多轮搜索生成研究报告 |
| "搜一下XX的网页存到知识库" | Pipeline 6 (--no-generate) |
需要导入知识库 |
| "XX是什么" / "帮我查一下XX" | Agent 自身搜索，不走 Pipeline 6 | 用户只想要答案，不涉及知识库 |
| "最近有什么XX的新闻" | Agent 自身搜索，不走 Pipeline 6 | 快速查询，无需存储 |
判断关键：用户的搜索意图是否涉及存储到知识库或生成产出物。涉及 → Pipeline 6；不涉及 → Agent 自行搜索回答。
搜索模式总览
| 模式 | type | source | 耗时 | 结果 |
|---|---|---|---|---|
| 快速搜索网页 | FAST_SEARCH |
WEB |
~4秒 | 10 个网页链接（contentType=WEBSITE） |
| 快速搜索论文 | FAST_SEARCH |
SCHOLAR |
~3秒 | 10 篇论文（contentType=PAPER，URL 指向 arxiv PDF） |
| 深度研究网页 | DEEP_RESEARCH |
WEB |
~2-5分钟 | 1 份研究报告（REPORT）+ N 个网页（WEBSITE） |
| 深度研究学术 | DEEP_RESEARCH |
SCHOLAR |
~5分钟 | 1 份报告 + N 篇论文 |
接口决策表
| 用户意图 | 执行方式 | 关键参数 |
|---|---|---|
| 搜网页并生成报告 | Pipeline 6 pipeline_web_search.py |
--kb --query --source WEB --output-type |
| 搜学术论文并生成综述 | Pipeline 6 | --kb --query --source SCHOLAR --output-type |
| 深度研究某个话题 | Pipeline 6 | --kb --query --type DEEP_RESEARCH |
| 搜索结果只存到知识库 | Pipeline 6 | --kb --query --no-generate |
| 只搜索看看有什么 | Pipeline 6 | --kb --query --search-only |
常用工作流
1. 快速搜索网页 → 导入 → 生成报告
python3 scripts/pipeline_web_search.py \
--kb "AI研究" --query "大模型 Agent 最新进展" \
--source WEB --output-type PDF
流程：搜索(~4s) → 10 个网页导入知识库 → 等待解析 → 提交 PDF 报告生成任务
2. 快速搜索学术论文 → 导入 → 生成
python3 scripts/pipeline_web_search.py \
--kb "论文集" --query "large language model agent" \
--source SCHOLAR --output-type MARKDOWN
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.
- 11d ago First seen · 122 lines · 39 tokens per session scan A 1501963cf839
happy-notes-search is a skill published in the GitHub repository iflow-ai/iflow-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,807 once invoked, about $0.0002 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.
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…