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 hydah/thequeen --skill review-litegit clone --depth 1 https://github.com/hydah/thequeenWrote 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/hydah/thequeen/review-lite)<a href="https://agentmods.dev/skills/hydah/thequeen/review-lite"><img src="https://agentmods.dev/badge/skills/hydah/thequeen/review-lite.svg" alt="Measured on agentmods" 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 | $0.00093 | $0.01143 |
| Opus 5 | $0.00046 | $0.00571 |
| Sonnet 5 | $0.00019 | $0.00229 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
review-lite 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 6d 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.
What it actually says
Review Lite
Overview
面向 manager 角色的轻量周回顾。
它解决的是"一周结束后,快速把事实拉平、把判断说清、把下周焦点定下来",而不是替代完整的管理反思系统。
与 full review 的边界:
- 不依赖
playbook/management/下的方法论文档 - 不依赖
context/current-focus.md或context/weekly-report-categories.md - 不做团队周报聚合、项目线分类、update 模式
- 不做季度/半年归档,只做当前周的一篇轻量回顾
When to Use
- 一周快结束了,想快速回顾这周推进得怎么样
- 想用 10-15 分钟做一次 manager 视角的轻量复盘
- 用户说"weekly review"、"周回顾"、"周复盘"、"快速回顾"、"轻量 review"
Workspace Contract
- 输出目录固定为
review/ - 当前周的默认文件名:
review/YYYY-Www.md(ISO 周) - 如果当前周文件已存在,优先更新,不重复创建多个同周文件
- 只允许写
review/下当前周文件,不写其他目录 - 事实输入优先来自:
todo/today.mdtodo/completed.mdscratch/scratch.md- 最近 7 天在
meeting/、decision/、customers/、question/下新增或修改的文档
如果某些目录不存在,直接跳过,不作为失败条件。
Workflow
Step 1: 收集事实
按顺序读取可用信息:
todo/today.md:看本周尾声还挂着什么todo/completed.md:提取本周完成记录scratch/scratch.md:识别尚未消化的信号- 扫描
meeting/、decision/、customers/、question/最近 7 天有无新增或更新文档
目标是先整理出事实层,不急着下判断。
Step 2: 形成五段草稿
基于已收集的事实,先起一个 5 段草稿:
- 本周推进:这周实际推进了什么
- 做对了什么:哪些判断或动作是有效的
- 风险与盲区:还有什么没看清、没推进或可能延迟爆雷
- 人与协作:这周在带人、协同或对外推进上有什么观察
- 下周定焦:下周最值得盯的 1-3 件事
Step 3: 轻量追问
最多追问 3 个问题,优先问最能提升质量的:
- 这周最该复盘的一件事是什么?
- 哪个风险你觉得还没处理到位?
- 下周最重要的一个结果是什么?
如果用户说"快速过"、"先出草稿",则跳过追问,直接生成并标注可补充项。
Step 4: 落盘
把结果写到当前周文件,建议结构:
# 2026 W15 周回顾
## 本周推进
- ...
## 做对了什么
- ...
## 风险与盲区
- ...
## 人与协作
- ...
## 下周定焦
1. ...
2. ...
3. ...
## 一句话提醒
> ...
如果文件已存在,更新对应 section,避免同一周多份重复文档。
Editing Rules
- 修改前先读取目标文件
- 优先使用当前 AI 工具提供的最小粒度编辑能力做精确修改
- 只写
review/下当前周文件 - 不创建季度/半年归档,不创建额外索引文件
- 不回写
todo/、decision/、customers/或index/
Quality Checklist
- 输出基于已读取到的事实,不凭空补工作项
- 至少包含五段:本周推进、做对了什么、风险与盲区、人与协作、下周定焦
- 缺失信息有显式标注,而不是假装完整
- 只写当前周 review 文件,没有扩散到其他目录
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.
- 6d ago First seen · 120 lines · 93 tokens per session scan A fc80b486e387
review-lite is a skill published in the GitHub repository hydah/thequeen (2 stars, last pushed 4mo ago), licensed MIT. It adds 93 tokens to every session and 1,143 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
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…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.