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 larksuite/meegle-cli --skill meeglegit clone --depth 1 https://github.com/larksuite/meegle-cliWrote 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/larksuite/meegle-cli/meegle)<a href="https://agentmods.dev/skills/larksuite/meegle-cli/meegle"><img src="https://agentmods.dev/badge/skills/larksuite/meegle-cli/meegle/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/larksuite/meegle-cli/meegle"><img src="https://agentmods.dev/badge/skills/larksuite/meegle-cli/meegle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00126 | $0.08604 |
| Opus 5.5 | $0.00050 | $0.03442 |
| Sonnet 5.5 | $0.00025 | $0.01721 |
| Haiku 4.5 | $0.00013 | $0.00860 |
Grade A, and why
meegle 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 13d 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 — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
飞书项目 (Meego/Meegle) 操作指南
本技能通过 Meegle CLI来操作飞书项目数据。输出语言跟随用户输入语言，默认中文。
各命令的调用示例见 references/api-examples.md。 授权流程（所有业务命令前必须执行）：见 references/auth-guard.md CLI 使用指南（命令结构、参数传递、命令发现）：见 references/cli-guide.md
Project 空间域
project search
搜索空间信息，将空间名转换为 project_key 或验证空间是否存在；省略 --project-key 时返回当前用户最近访问过的空间列表（按访问时间由近及远）。
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| --project-key | string | 否 | 空间 projectKey、simpleName 或空间名称；留空查询当前用户可访问的空间 |
| --page-num | number | 否 | 分页页码，每页 50 条，从 1 开始 |
WorkItem 工作项域
元数据查询命令（
workitem meta-types/workitem meta-fields/workitem meta-roles/workitem meta-create-fields）的参数表见 references/workitem.md。
workitem create
创建工作项实例。务必先用 workitem meta-fields 获取字段信息，workitem meta-roles 获取角色信息。模板 ID 是必填项。
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| --work-item-type | string | 是 | 工作项类型 |
| --project-key | string | 否 | 空间标识 |
| --fields | array | 否 | 字段值列表，每项含 field_key 和 field_value |
workitem get
按 ID/名称查询工作项概况。不传 fields 时返回固定基础字段加上一组默认系统字段：group_type（拉群方式）、description、current_status_operator、watchers（value 为 null 时也会出现）；其余字段需先通过 workitem meta-fields 拿到 key 再传入 fields。
| 参数 | 类型 | 必填 | 说明 |
|---|---|---|---|
| --work-item-id | string | 否 | 工作项 ID（与 --name 二选一） |
| --name | string | 否 | 按名称查询工作项（与 --work-item-id 二选一） |
| --project-key | string | 否 | 空间 key |
| --fields | array | 否 | 要查询的 field_key 或 field_name；传 ["_all"] 时按逻辑字段分页返回全部字段；传 ["group_type"] 时只取拉群方式 |
| --page-size | number | 否 | 仅 fields=["_all"] 时生效；每页字段数量，默认 100，最大 200。Meegle CLI 序列化约束：--page-size N 会被序列化为字符串触发后端 need I64 type, but got: STRING；必须走 --params '{"page_size":N}' 以数字传出 |
| --page-token | string | 否 | 仅 fields=["_all"] 时生效；翻页 token，首次不传，下一页传上一页响应的 next_page_token（token 形如字段 key，例如 "business"）；同上，须走 --params '{"page_token":"..."}' |
What ships with it
26 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/ai-handoff.md 5.9 KB
- references/api-examples.md 9.9 KB
- references/attachment.md 9.2 KB
- references/auth-guard.md 4.5 KB
- references/cli-guide.md 2.5 KB
- references/error-handling.md 10 KB
- references/field-value-extras.md 1.5 KB
- references/misc.md 6.5 KB
- references/mql-basics.md 5.3 KB
- references/mql-examples.md 4.7 KB
- references/mql-nodes-relations.md 5.5 KB
- references/mql-operators.md 6.9 KB
- references/mql-people-roles.md 3.7 KB
- references/mql-time-status.md 3.5 KB
- references/performance.md 1.1 KB
- references/rich-text-editor-markdown-syntax.md 12 KB
- references/sop-create-workitem.md 10.0 KB
- references/sop-transition-node.md 14 KB
- references/sop-transition-state.md 8.4 KB
- references/sop-update-workitem.md 12 KB
- references/url-kinds.md 6.3 KB
- references/url-links.md 8.3 KB
- references/view.md 1.4 KB
- references/wbs.md 12 KB
- references/workflow.md 1.8 KB
- references/workitem.md 1.8 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.
- 13d ago Changed · +2 lines ba28e6584f28
- 27d ago Changed · +1 lines ab2ab36b7081
- 1mo ago Changed · -1 lines 246279c1a9bb
- 1mo ago First seen · 468 lines · 126 tokens per session scan A 01355dee93b3
meegle is a skill published in the GitHub repository larksuite/meegle-cli (245 stars, last pushed 2d ago), licensed MIT. It adds 126 tokens to every session and 8,604 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
project-ops
Use when an operator wants to run a small or mid-sized project from a flat file instead of standing up Jira or Asana — dated milestones each with one named owner and a binary done-test, rule-driven RAG status, a RAID log, slippage detection, and a two-minute weekly status report. NOT sequencing the engineering work…
jjj
Use when working in Jujutsu repositories for problem tracking, solution management, and code review — implements Popperian epistemology (problems → solutions → critiques) directly in version control.
planr-sprint
Refine every open backlog item against the code and the calendar, refute the picks, and select a sprint that fits capacity and the release cut. Use before a cut or sprint; not for decomposing one specification or reporting status.
planr-operate
Run a focused operating review across seven executive lenses and produce a decision and action brief. Use for periodic product or company-level leadership review.
planr-chair-review
Synthesize an Operate cycle into a prioritized decision queue and action plan. Use after specialist reviews when leadership needs one coherent brief.
planr-challenger-review
Challenge an Operate cycle's claims, alternatives, downside, and confidence. Use when assumptions or executive consensus need an independent stress test.