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 iflow-ai/iflow-skills --skill happy-notesgit clone --depth 1 https://github.com/iflow-ai/iflow-skillsWrote 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/happy-notes)<a href="https://agentmods.dev/skills/iflow-ai/iflow-skills/happy-notes"><img src="https://agentmods.dev/badge/skills/iflow-ai/iflow-skills/happy-notes/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/happy-notes"><img src="https://agentmods.dev/badge/skills/iflow-ai/iflow-skills/happy-notes.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 | $0.00309 | $0.07488 |
| Opus 5 | $0.00154 | $0.03744 |
| Sonnet 5 | $0.00062 | $0.01498 |
| Haiku 4.5 | $0.00031 | $0.00749 |
Grade A, and why
happy-notes scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| 用 `curl`/`iflow_api` 直接拼 HTTP 请求调 API（如 `creationList`、`shareNotebook` 等） | **必须使用 Pipeline 脚本**。Pipeline 已封装凭证、参数校验、轮询、错误重试。直接调 API 容易出错且不稳定。所有 20 个 API 端点均已有 Pipeline 覆盖，不存在"需要直接调 API"的场景 | How it starts
The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.
happy-notes
iflow 知识库助手。支持：knowledge-base（知识库管理与文件管理）、reports（内容生成）、search（联网搜索并导入知识库）。分享功能见下方「分享功能」章节。
Setup
Security note: Credentials are only sent as HTTP headers to the configured API endpoint and never to any other domain.
- 获取 API Key：访问 API Key 管理页面 申请
- 存储凭证（二选一）：
# 方式 A — 配置文件（推荐，Linux/Mac）
mkdir -p ~/.config/happy-notes && echo "your_api_key" > ~/.config/happy-notes/api-key
# 方式 B — 环境变量
export IFLOW_API_KEY="your_api_key"
# Windows PowerShell 用户：
New-Item -ItemType Directory -Force -Path "$env:USERPROFILE\.config\happy-notes"
"your_api_key" | Out-File -FilePath "$env:USERPROFILE\.config\happy-notes\api-key" -Encoding utf8 -NoNewline
# 或设置环境变量：$env:IFLOW_API_KEY = "your_api_key"
Windows 用户注意：必须先创建
happy-notes目录再写入 api-key 文件。如遇配置问题，请访问 API Key 管理页面 获取帮助。
Agent 按优先级尝试：环境变量 → 配置文件。Pipeline 脚本内部自动读取凭证，无需手动初始化。
快速决策树
收到用户请求后，按顺序判断：
1. 用户只是问问题/查信息？ → 不走 Pipeline，Agent 自行回答
2. 操作主体是什么？
a. 知识库本身（列表/创建/删除/改名/详情） → pipeline_kb.py
b. 知识库中的文件（列表/重命名/删除/详情/重试） → pipeline_file_management.py
c. 需要新建库 + 上传文件/URL → P1 (pipeline_create_kb_and_generate.py)
d. 向已有库追加内容（文件/URL/文本） → P3 (pipeline_import_and_generate.py)
e. 在已有库中搜索内容 → 核心目的是生成? P2 : P4
f. 联网搜索外部网页/论文 → P6 (pipeline_web_search.py)
g. 直接对已有库生成报告/PPT → pipeline_generate.py
h. 查看生成进度 → pipeline_check_status.py
i. 分享知识库 → pipeline_share.py
快速决策表
⚡ 多步骤任务优先用 Pipeline 脚本。Pipeline 已封装凭证读取、参数串联、解析轮询、错误处理，一条命令完成整个流程。仅 Pipeline 不覆盖的单步操作才直接调 API（见下方「直接调 API 参考」）。
收到用户请求后，按此表选择执行方式：
| 用户意图 | 执行方式 | 关键参数 |
|---|---|---|
| 建库 + 上传 + 生成 | ||
| "建个知识库，传几篇论文，生成报告" | Pipeline 1 pipeline_create_kb_and_generate.py |
--name --files --urls --output-type --query |
| "建个知识库存一下这些文件"（不生成） | Pipeline 1 | --name --files --no-generate |
| 追加内容 + 生成 | ||
| "把这个链接/文件加到XX知识库，然后生成总结" | Pipeline 3 pipeline_import_and_generate.py |
--kb + --files/--urls/--text --output-type --query |
| "帮我把这段内容存到知识库" | Pipeline 3 | --kb --text --text-title --rename --no-generate |
| 搜索 + 生成 | ||
| "在XX知识库里搜一下关于YY的，生成报告" | Pipeline 2 pipeline_search_and_generate.py |
--kb --search --mode semantic --output-type --query |
| "搜一下知识库里有没有关于XX的文件" | Pipeline 2 | --kb --search --mode file --search-only |
| 语义检索（深度内容匹配） | ||
| "知识库里有没有关于XX的内容" | Pipeline 4 pipeline_semantic_search.py |
--kb --query |
| "找到相关内容后生成报告" | Pipeline 4 | --kb --query --generate --output-type |
| "检索后分享知识库" | Pipeline 4 | --kb --query --share |
| 文件管理 | ||
| "看看知识库里有哪些文件" | Pipeline 5 pipeline_file_management.py list |
--kb |
| "把这个文件改个名" | Pipeline 5 rename |
--kb --file --new-name |
| "删掉这个文件" | Pipeline 5 delete |
--kb --file --force |
| "把那几个测试文件都删了" | Pipeline 5 batch-delete |
--kb --files --force |
| 联网搜索 + 导入 + 生成（搜索结果存入知识库） | ||
| "帮我搜一下关于XX的网页，整理成报告" | Pipeline 6 pipeline_web_search.py |
--kb --query --source WEB --output-type |
| "搜一下XX的学术论文，生成综述" | Pipeline 6 | --kb --query --source SCHOLAR --output-type |
| "深度研究一下XX" | Pipeline 6 | --kb --query --type DEEP_RESEARCH |
| "搜一下XX的论文存到知识库"（不生成） | Pipeline 6 | --kb --query --no-generate |
| "搜一下XX看看有什么"（只看结果） | Pipeline 6 | --kb --query --search-only（⚠️ 仍需知识库） |
| 快速搜索（不涉及知识库） | ||
| "XX是什么" / "帮我查一下XX" / "最近有什么关于XX的新闻" | 不走 Pipeline，Agent 使用自身搜索能力直接回答 | — |
| 知识库管理 | ||
| 查看/创建/删除知识库 | pipeline_kb.py list/create/delete |
--name / --kb --force |
| 修改知识库名称/描述 | pipeline_kb.py update |
--kb --name --description |
| 查看知识库详情 | pipeline_kb.py info |
--kb |
| 文件管理补充 | ||
| 查看文件详情 | pipeline_file_management.py info |
--kb --file |
| 重试解析失败的文件 | pipeline_file_management.py retry |
--kb --file |
| 内容生成（单独生成，不含搜索/导入） | ||
| "帮我做个PPT" / "生成一份报告" | pipeline_generate.py |
--kb --output-type --query --preset |
| "做个 AI 视频" / "生成短视频" | pipeline_generate.py |
--kb --output-type HHVIDEO --query --video-*（详见脚本 --help） |
| "出几道题" / "做个测验" / "考考我" | pipeline_generate.py |
--kb --output-type QUIZ --query（题量/难度写进 query） |
| "做张信息图" / "数据可视化" | pipeline_generate.py |
--kb --output-type GRAPH --query（风格/尺寸写进 query） |
| "翻译这个文档" / "中译英" | pipeline_generate.py |
--kb --output-type TRANSLATION --query（源/目标语言写进 query） |
| "修改这页 PPT" / "重做第 N 页" | pipeline_generate.py |
--kb --output-type PPT_EDIT --query（需要前序 PPT 上下文） |
| "查看生成进度" / "做好了吗" | pipeline_check_status.py |
--kb [--creation-id] |
| 搜索管理 | ||
| 停止正在进行的搜索 | pipeline_web_search.py --stop |
--kb --stop |
| 删除搜索记录 | pipeline_web_search.py --delete-search |
--kb --delete-search |
| 分享 | ||
| "把知识库分享给同事" | pipeline_share.py |
--kb |
| 其他（极少数 Pipeline 未覆盖的操作） | ||
| 修改知识库高级设置等 | 查阅 references/api.md |
仅作为最后手段 |
What ships with it
29 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.
- evals/evals.json 31 KB
- examples/add-file-then-generate.md 2.8 KB
- examples/long-task-async.md 2.7 KB
- examples/ppt-with-preset.md 2.0 KB
- examples/search-then-generate.md 2.6 KB
- examples/semantic-search.md 3.2 KB
- examples/share-knowledge-base.md 1.3 KB
- examples/student-literature-review.md 3.5 KB
- examples/text-import.md 2.4 KB
- examples/web-search-deep.md 3.3 KB
- examples/web-search-fast.md 3.0 KB
- knowledge-base/SKILL.md 14 KB
- README.md 5.6 KB
- references/api.md 23 KB
- references/kb-matching.md 3.1 KB
- references/pipelines.md 16 KB
- reports/SKILL.md 18 KB
- scripts/iflow_common.py 25 KB runs code
- scripts/pipeline_check_status.py 1.8 KB runs code
- scripts/pipeline_create_kb_and_generate.py 4.8 KB runs code
- scripts/pipeline_file_management.py 9.4 KB runs code
- scripts/pipeline_generate.py 5.2 KB runs code
- scripts/pipeline_import_and_generate.py 7.9 KB runs code
- scripts/pipeline_kb.py 6.4 KB runs code
- scripts/pipeline_search_and_generate.py 4.9 KB runs code
- scripts/pipeline_semantic_search.py 4.7 KB runs code
- scripts/pipeline_share.py 1.1 KB runs code
- scripts/pipeline_web_search.py 10 KB runs code
- search/SKILL.md 6.2 KB
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.
- 10d ago First seen · 386 lines · 309 tokens per session scan A 4fb01f78a435
happy-notes is a skill published in the GitHub repository iflow-ai/iflow-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 309 tokens to every session and 7,488 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.