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 Zaoqu-Liu/ScienceClaw --skill medge-dashboardgit clone --depth 1 https://github.com/Zaoqu-Liu/ScienceClawWrote 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/zaoqu-liu/scienceclaw/medge-dashboard)<a href="https://agentmods.dev/skills/zaoqu-liu/scienceclaw/medge-dashboard"><img src="https://agentmods.dev/badge/skills/zaoqu-liu/scienceclaw/medge-dashboard/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/zaoqu-liu/scienceclaw/medge-dashboard"><img src="https://agentmods.dev/badge/skills/zaoqu-liu/scienceclaw/medge-dashboard.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 | $0.00000 | $0.02156 |
| Opus 5 | $0.00000 | $0.01078 |
| Sonnet 5 | $0.00000 | $0.00431 |
| Haiku 4.5 | $0.00000 | $0.00216 |
Grade A, and why
medge-dashboard 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 7d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local Research Dashboard Skill
概述
每次科研任务开始时，生成一个临时的本地 dashboard，动态展示任务关键信息和产物预览。
组件
state.json：数据协议，openclaw 负责写入和更新dashboard.html：本地单文件页面，轮询 state.json 并渲染dashboard_serve.py：静态文件服务器，serve 任务根目录
所有文件放在任务独立目录中（如 data/<task_name>/dashboard/）。
state.json Schema
{
"title": "任务标题",
"updated_at": "2024-01-01 12:00:00",
"panels": [
{
"type": "progress|text|list|code|table|image|files|step",
"label": "面板标题（可折叠的标识）",
"content": "内容（格式取决于 type）"
}
]
}
Panel 类型说明
| type | content 格式 | 用途 | 渲染 |
|---|---|---|---|
progress |
number (0-100) | 整体进度 | 置顶在 header，不出现在面板区 |
text |
string | 状态描述、摘要、发现 | 预格式化文本，自动换行 |
list |
string[] | 步骤列表、待办、已完成项 | 带左边框的条目列表 |
code |
string | 代码片段、命令输出 | 等宽字体，可滚动，带复制按钮 |
table |
{src: "path"} 或 {headers: [...], rows: [...]} |
CSV/统计结果 | 从文件实时加载或内嵌数据 |
image |
string 或 string[] | 图片产物预览 | 内联图片，点击放大，带下载按钮 |
files |
string[] 或 {name, size}[] |
输出目录文件列表 | 可点击预览/下载的文件列表 |
step |
{desc, code?, outputs?} |
步骤卡片：展示一个分析步骤的代码和产物 | 代码 + 产物预览 + 描述 |
step 类型（核心面板）
目标： 每个分析步骤 = 做了什么 + 跑了什么代码 + 产出了什么
{
"type": "step",
"label": "① 数据加载与清洗",
"content": {
"desc": "加载 CHARLS .dta 数据，编码 8 项 ACE 指标...",
"code": "import pandas as pd\ndf = pd.read_stata('charls.dta')\n...",
"outputs": [
{"kind": "text", "value": "原始 96,628 行 → 筛选后 46,628 行（12,877 人）"},
{"kind": "image", "src": "/output/fig1_ace_distribution.png", "caption": "ACE 评分分布"},
{"kind": "table", "src": "/output/table1_baseline.csv", "caption": "基线特征"},
{"kind": "file", "src": "/output/table1_baseline.csv"}
]
}
}
step.content 字段
| 字段 | 必填 | 说明 |
|---|---|---|
desc |
✅ | 这步做了什么、发现了什么（完整句子） |
code |
可选 | 核心代码片段（默认折叠，展示关键逻辑） |
code_file |
可选 | 完整脚本文件路径（如 /analysis.py），前端按需加载 |
outputs |
可选 | 产物列表 |
约定：
code放精华片段帮助快速理解逻辑；code_file指向完整可运行的脚本。两者可同时存在。
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.
- 7d ago First seen · 207 lines · 0 tokens per session scan A 6f22166f8021
medge-dashboard is a skill published in the GitHub repository Zaoqu-Liu/ScienceClaw (60 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,156 tokens. 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 2026-09-03.
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.