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 agentmods add skills/peiiii/nextclaw/visualize-outputnpx skills add Peiiii/nextclaw --skill visualize-outputgit clone --depth 1 https://github.com/Peiiii/nextclawWrote 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/peiiii/nextclaw/visualize-output)<a href="https://agentmods.dev/skills/peiiii/nextclaw/visualize-output"><img src="https://agentmods.dev/badge/skills/peiiii/nextclaw/visualize-output.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 | $0.02776 |
| Opus 5 | $0.00046 | $0.01388 |
| Sonnet 5 | $0.00019 | $0.00555 |
| Haiku 4.5 | $0.00009 | $0.00278 |
Grade A, and why
visualize-output 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize Output
让可视化服务于理解,而不是只增加装饰。始终选择能够清楚表达结果的最小展示方式;如果普通文字已经足够,就不要为了“好看”强行可视化。
选择展示方式
- 简单事实、结论或短步骤:使用自然的 Markdown 段落或短列表。
- 多组精确映射、字段比较或数值对照:使用紧凑表格。
- 流程、时序、层级、依赖或状态迁移:优先使用聚焦的 Mermaid 图。
- 需要真实视觉形象、空间构图或插画表达:在具备图片生成/处理能力时使用图片。
- 布局、排版、图形编码或轻量交互能显著提升理解:使用自包含的内联 HTML。
- 可复用应用、编辑器、管理台、大表格、多页界面或持续工作流:不要塞进当前回答;读取
nextclaw-app-creator,改用 Panel App / side panel。
同一关系默认只选一种主要可视化,不要把表格、Mermaid 和 HTML 重复堆叠。必要的文字说明保持简短,并让可视化本身承担主要信息表达。
单一焦点
- 一个可视化只回答一个主要问题,突出一个核心结论或一组紧密相关的数据。
- 默认不要制作带导航、侧栏、标签页、工具栏和多块 KPI 的“大而全 dashboard”。
- 使用留白、对齐、字号和必要的细分隔线建立层级;不要靠页标题、总背景板或把每一组内容包成卡片来制造结构。
- 如果内容无法在一个聚焦表面里讲清,先删减、分层摘要,或改用 side panel;不要缩小到难以阅读。
内联 HTML 合同
仅当 HTML 比 Markdown / Mermaid 明显更清楚时使用:
- 先创建目标文件的父目录,再创建一个真实存在、可独立打开的
.html文件;写入后确认文件存在。只为当前会话展示而生成的可视化属于 NextClaw 持久资产,必须放到系统上下文给出的NEXTCLAW_HOME/assets/visualizations/<session-id>/绝对目录,并在声明中使用绝对路径。不得放到/tmp、其他临时目录、当前项目或工作目录根部;只有用户明确要求项目交付文件时,才写入用户项目。 - 默认把 CSS、JavaScript 和 SVG 内联在文件中,不依赖 CDN、远程字体、远程脚本或不可验证的网络资源。
- 在最终回复中输出 inert 的
nextclaw-inline声明,让宿主把文件直接渲染在消息内。当前任务生成的本地 HTML 必须使用filetarget;禁止改成urltarget,也不要把本地路径伪造成/somewhere/file.html:
{"target":{"type":"file","payload":{"path":"/Users/example/.nextclaw/assets/visualizations/session-123/result.html","viewer":"rendered"}},"title":"Result"}
- 一旦选择用内联 HTML 交付当前回答,无论用户是否说出“内联”,整个回合都不得调用
show_file、show_url、系统浏览器或其他外部展示动作。show_file(path, viewer="rendered")会打开 side panel,不能用来预览、验证或展示内联结果;用read_file/exec检查文件和内容,最终只输出上面的 Markdown 声明。只有明确决定不做内联、需要长时间阅读或操作时才改用 side panel。 - 最终回复仍要自包含,但不要用表格、列表、数据速览或第二种图表重复内联视觉已经表达的数据。最终一次验证工具返回后,静默完成判断,不得输出核对表、计算过程、“检查通过”、引导语或数据复述;最终可见内容必须只有
nextclaw-inline声明,声明的关闭围栏就是回复最后内容。不要描述它位于“右侧”“侧栏”或其他未经执行的 UI 位置。
```nextclaw-inline
{"target":{"type":"file","payload":{"path":"/Users/example/.nextclaw/assets/visualizations/session-123/result.html","viewer":"rendered"}},"title":"Result"}
```
HTML 画布合同
- 把整个 HTML 文档当成唯一展示表面。
html/body默认保持透明、无边框、无阴影,只有承载内容所需的内边距;不要再放带背景、外边框、圆角或阴影的根容器。 - 默认不放可见的页面标题、眉题、报告名或说明横幅,直接从核心图形与数据开始。只有标题本身是用户要求展示的信息时才保留;
nextclaw-inline.title只是宿主元数据,不得在 HTML 中重复渲染。 - 不要在 HTML 内重复文件名、预览标题栏、打开按钮或工具栏;宿主会在外部提供这些操作,并负责圆角裁切。
- 使用响应式宽度、
box-sizing: border-box和自然文档高度;禁止固定桌面宽度、横向滚动和依赖超宽画布。 - 宿主从约
240px高度开始按内容增长,可见上限为min(90vh, 1440px)。优先把完整核心信息控制在一屏内,并确保不超过1440px仍能理解。 - 不依赖 document 级内部滚动。若内容超过可见上限,先删减、改成摘要或换 side panel;只有短列表、下拉菜单等局部控件可以有限滚动。
- 页面本身就是视觉容器。内部需要分组时优先用间距、对齐、排版或细分隔线。默认不使用 KPI 卡片、洞察框、章节卡片或其他带独立背景/边框/阴影的矩形容器;只有某个形状本身承担数据编码或交互含义时才使用色块。
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.
- 2d ago First seen · 93 lines · 93 tokens per session scan A 1bab1c121b24
visualize-output is a skill published in the GitHub repository Peiiii/nextclaw (254 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 2,776 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 2026-09-03.
Other skills, from other repositories
ha-mac-control
Hope Agent native macOS desktop control — the standard maccontrol status / diagnostics / apps / dock / spaces / snapshot / visual / windows / menu / clipboard / dialog loop, target-first action rules, no-blind-coordinate policy, and recovery for stale AX/window/menu/dialog state. Load whenever using maccontrol, or…
ha-skill-creator
Create, edit, improve, or audit Hope Agent skills. Use when the user wants to: (1) create a new skill from scratch, (2) edit or improve an existing skill, (3) review or clean up a SKILL.md file, (4) run evaluations to test skill effectiveness, (5) optimize skill descriptions for better trigger accuracy. Trigger…
ha-browser
Hope Agent browser automation — the standard status → tabs → snapshot → act loop, stale-ref recovery rules, and what to do when login / 2FA / captcha / camera-prompt / dialog blocks progress. Load this skill whenever you reach for the browser tool. Trigger on: user asks the agent to open / control / click / scrape /…
ha-logs
Self-service diagnostics — query Hope Agent's local SQLite databases (logs / sessions / background jobs) directly via the exec tool to investigate problems, analyze usage, and locate root causes. Trigger on: user reports something broken / failing / slow / stuck / not responding ('X 不工作', 'X 报错', 'X 卡住', '为什么 X 失败'…
ha-pet-import
Safely import, select, switch, or enable a compatible desktop pet in Hope Agent. Resolve packages from any origin, including local folders, zip archives, pet.json plus a sprite, PNG/WebP atlases, chat attachments, repository or cloud files, direct HTTPS artifact URLs, and download pages. Use whenever a user asks to…
ha-data-analytics
Hope-native local-first data analysis and Artifact reporting. Use for CSV/XLSX analysis, KPI readouts, metric diagnosis, product/business analysis, data-quality review, dashboards, charts, analytical reports, 数据分析, 指标诊断, 数据质量, 分析报告, or when the user wants a shareable offline HTML/ZIP/Markdown/PDF result. Produces the…