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 wecomcli-contactgit 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/wecomcli-contact)<a href="https://agentmods.dev/skills/pinvou/pinvou-agent/wecomcli-contact"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/wecomcli-contact/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/wecomcli-contact"><img src="https://agentmods.dev/badge/skills/pinvou/pinvou-agent/wecomcli-contact.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 | $0.00092 | $0.01004 |
| Opus 5.5 | $0.00037 | $0.00402 |
| Sonnet 5.5 | $0.00018 | $0.00201 |
| Haiku 4.5 | $0.00009 | $0.00100 |
Grade A, and why
wecomcli-contact 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 22d 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.
This is a copy
92% identical to wecomcli-contact — 6 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.
What it actually says
企业微信联系人搜索
执行任何
wecom-cli命令前，必须先读取并完成wecomcli-shared技能的公共前置检查。
使用 wecom-cli 按关键词搜索企业微信通讯录中的人员。
接口
按关键词批量模糊搜索人员，一次最多 10 个关键词，返回命中 users 数组（姓名 / 英文名 / 职务 / 部门）。关键词可匹配的字段包括：姓名（用户名）、姓名拼音、英文名、别名，而不仅限于中文名和别名。
命令
wecom-cli contact users search --json '<JSON 参数>'
参数
| 字段 | 类型 | 必填 | 默认值 | 语义 |
|---|---|---|---|---|
keywords |
string[] | 是 | — | 搜索关键词列表，可按姓名（用户名）/ 拼音 / 英文名 / 别名匹配，最多 10 个；多个关键词之间是 OR 关系 |
search_mode |
string | 否 | — | 搜索模式，默认不传该参数；仅当需要命中列表（清点 / 穷举意图）时，才显式传 "list" |
- 默认（不传
search_mode）：返回最相关的候选结果，用于常规按名 / 拼音等查单个人的场景，绝大多数场景走此分支。 - 传
search_mode = "list"：列表模式，返回命中结果列表而不只取最相关前几条，仅当用户明确要清点 / 穷举时才传，典型话术如"一共有几个张三 / 所有叫李四的人 / 列出全部同名 / 全部同名人员"等；此时不受"前 5 位"展示上限约束。列表可能因服务端限制未完整返回，以返回的hint字段为准：hint给出限制说明时，必须向用户如实说明结果可能不全，不得把返回条数当作准确总数。
返回
| 字段 | 类型 | 说明 |
|---|---|---|
users |
array | 命中的用户列表 |
users[].userid |
string | 用户唯一标识 |
users[].name |
string | 中文姓名 |
users[].alias |
string | 英文名 / 别名（可能为空） |
users[].email |
string | 邮箱（可能为空） |
users[].position |
string | 管理职务（如"负责人"），不是"职位"（可能为空） |
users[].matched_keywords |
string[] | 本条 user 命中的请求关键词 |
users[].departments |
string[] | 所在部门路径列表（从大到小），主部门靠前 |
hint |
string | 结果限制提示（可能为空）：当某个关键词的命中结果因限制未完整返回时，接口会在此字段给出说明 |
users_count |
integer | users 数组元素数量 |
使用规则
- 歧义展示上限：同一关键词下候选超过 5 位时，只展示前 5 位（附姓名 / 英文名 / 职务等区分信息），告知用户"若目标不在其中可要求『查看更多』"，仅在用户明确要求时再展开下一批；
- 展示顺序：必须严格按照接口返回
users数组的原始顺序展示，不得自行随机排序、重排或打乱次序。 - 结果限制提示：当返回中 hint 字段非空时，必须在回复中告知用户"当前返回内容有限，仅返回了部分结果"，并可结合 hint 内容说明受限原因。
缺少参数
必填参数缺失（未提供搜索关键词）且上下文无法推断时，用简洁自然语言向用户追问缺失信息，不得猜测默认值。
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.
- 22d ago Changed · -4 tokens per session ac2caa182f3a
- 2mo ago First seen · 59 lines · 96 tokens per session scan A 3beb9228b109
wecomcli-contact is a skill published in the GitHub repository Pinvou/pinvou-agent (2,764 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 1,004 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to wecomcli-contact, differing in 6 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.
create-agent
A guide for creating coding-agent definition files, including their metadata, format, setup process, and suggested agent types.
infographic
A guide for creating infographics with only HTML and CSS. Infographics present structured information visually, such as timelines, comparisons, funnels and organisation charts.
pptx
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
init
A project-initialisation guide that checks the project first, analyses its structure and creates an abu.md file with project rules.
prd-doctor
A structured review of a PRD, or product requirements document, and related feature specifications. It produces a concrete list of issues rather than a general opinion.