Pinvou/pinvou-agent is an open-source desktop workspace where an AI agent helps with work, visual design, and software development. People use it to work with files and knowledge, create editable visual artifacts, connect coding agents to projects, and extend the workspace with tools, MCP servers, skills, and workflows; the catalogue skills add capabilities to that environment.
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 Pinvou/pinvou-agent --skill lark-imgit clone --depth 1 https://github.com/Pinvou/pinvou-agentWrote 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/pinvou/pinvou-agent/lark-im)<a href="https://agentmods.dev/skills/pinvou/pinvou-agent/lark-im"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/lark-im/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/pinvou/pinvou-agent/lark-im"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/lark-im.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 | $0.00182 | $0.04774 |
| Opus 5 | $0.00091 | $0.02387 |
| Sonnet 5 | $0.00036 | $0.00955 |
| Haiku 4.5 | $0.00018 | $0.00477 |
Grade A, and why
lark-im 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 today.
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.
This is a copy
81% identical to lark-im — 80 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
im (v1)
CRITICAL — 开始前 MUST 先用 read 读取 ../lark-shared/SKILL.md,其中包含认证、权限处理
Core Concepts
- Message: A single message in a chat, identified by
message_id(om_xxx). Supports types: text, post, image, file, audio, video, sticker, interactive (card), share_chat, share_user, merge_forward, etc. - Chat: A group chat or P2P conversation, identified by
chat_id(oc_xxx). - Thread: A reply thread under a message, identified by
thread_id(om_xxx or omt_xxx). - Reaction: An emoji reaction on a message.
- Flag: A bookmark on a message or thread.
- Feed Shortcut: A chat pinned to the current user's feed sidebar, identified by
feed_card_id(anoc_xxxopen_chat_id for CHAT type). - Feed Group: A tag that groups feed cards in the feed list, identified by
feed_group_id(ofg_xxx). Members are feed cards, each identified byfeed_id+feed_type. Two types:normal(members managed explicitly) andrule(members auto-derived from rules).
Resource Relationships
Chat (oc_xxx)
├── Message (om_xxx)
│ ├── Thread (reply thread)
│ ├── Reaction (emoji)
│ └── Resource (image / file / video / audio)
└── Member (user / bot)
Important Notes
Identity and Token Mapping
身份规则见 lark-shared。IM 特有注意:同一 API 用 user/bot 可能一成一败(群成员关系、群主/管理员、租户边界都按当前调用者校验)。
Sender Name Resolution
When fetching messages (+chat-messages-list, +threads-messages-list, +messages-mget, +messages-search), the CLI shows a display name for both user and bot senders:
- Server-provided name: the read APIs return
sender_name(plus the full-i18nsender_i18n_namesmap) on each messagesender; the CLI surfaces it as the sender'snamefor users and bots alike. No name lookup and no extra permission are needed — no contact scope and noapplication:bot.basic_info:read. - Fallback to id: when the server does not provide a name, the sender is shown by its id and the command still exits 0. There is no contact-directory fallback.
What ships with it
59 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.
- references/card/card-2.0-schema.md 6.0 KB
- references/card/components/button.md 2.8 KB
- references/card/components/chart.md 2.2 KB
- references/card/components/checker.md 1.9 KB
- references/card/components/collapsible_panel.md 1.8 KB
- references/card/components/column_set.md 2.5 KB
- references/card/components/date_picker.md 1.6 KB
- references/card/components/div.md 1.7 KB
- references/card/components/form.md 2.2 KB
- references/card/components/header.md 1.6 KB
- references/card/components/hr.md 425 B
- references/card/components/img_combination.md 1.0 KB
- references/card/components/img.md 1.4 KB
- references/card/components/input.md 2.0 KB
- references/card/components/interactive_container.md 2.2 KB
- references/card/components/markdown.md 3.2 KB
- references/card/components/multi_select_person.md 1.6 KB
- references/card/components/multi_select_static.md 1.6 KB
- references/card/components/overflow.md 1.5 KB
- references/card/components/person_list.md 1.2 KB
- references/card/components/person.md 907 B
- references/card/components/picker_datetime.md 1.5 KB
- references/card/components/picker_time.md 1.5 KB
- references/card/components/recycling_container.md 1.5 KB
- references/card/components/select_img.md 1.9 KB
- references/card/components/select_person.md 1.5 KB
- references/card/components/select_static.md 1.8 KB
- references/card/components/table.md 2.1 KB
- references/card/lark-im-card-create.md 11 KB
- references/card/lark-im-card-style.md 18 KB
- references/card/resource/colors.md 1.4 KB
- references/card/resource/icons.md 2.3 KB
- references/lark-im-card-action-reply.md 9.5 KB
- references/lark-im-chat-create.md 7.9 KB
- references/lark-im-chat-identity.md 3.4 KB
- references/lark-im-chat-list.md 9.3 KB
- references/lark-im-chat-members-list.md 5.1 KB
- references/lark-im-chat-messages-list.md 10 KB
- references/lark-im-chat-search.md 8.3 KB
- references/lark-im-chat-update.md 3.4 KB
- references/lark-im-feed-group-list-item.md 3.1 KB
- references/lark-im-feed-group-list.md 2.7 KB
- references/lark-im-feed-group-query-item.md 2.3 KB
- references/lark-im-feed-groups.md 18 KB
- references/lark-im-feed-shortcut-create.md 4.2 KB
- references/lark-im-feed-shortcut-list.md 5.0 KB
- references/lark-im-feed-shortcut-remove.md 2.1 KB
- references/lark-im-flag-cancel.md 2.9 KB
- references/lark-im-flag-create.md 2.6 KB
- references/lark-im-flag-list.md 4.6 KB
- references/lark-im-message-enrichment.md 6.9 KB
- references/lark-im-messages-mget.md 4.3 KB
- references/lark-im-messages-reply.md 16 KB
- references/lark-im-messages-resources-download.md 3.8 KB
- references/lark-im-messages-search.md 13 KB
- references/lark-im-messages-send.md 18 KB
- references/lark-im-reactions.md 10 KB
- references/lark-im-scopes.md 2.2 KB
- references/lark-im-threads-messages-list.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.
- today Changed 61a72046678a
- 2d ago Changed 03fbf24715cf
- 10d ago First seen · 213 lines · 182 tokens per session scan A 63b7278d8886
lark-im is a skill published in the GitHub repository Pinvou/pinvou-agent (1,779 stars, last pushed today), licensed MIT. It adds 182 tokens to every session and 4,774 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to lark-im, differing in 80 lines, and is treated as a copy.
Other skills, from other repositories
schedule
A skill for creating and managing scheduled tasks, including tasks that run automatically at regular times.
skill-creator
A skill for creating, editing, improving, and testing skills for coding agents.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
docx
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
doc-coauthoring
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…