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 kachofugetsu09/akashic-agent --skill visualizegit clone --depth 1 https://github.com/kachofugetsu09/akashic-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/kachofugetsu09/akashic-agent/visualize)<a href="https://agentmods.dev/skills/kachofugetsu09/akashic-agent/visualize"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/visualize/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/kachofugetsu09/akashic-agent/visualize"><img src="https://agentmods.dev/badge/skills/kachofugetsu09/akashic-agent/visualize.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 | $0.00095 | $0.01817 |
| Opus 5.5 | $0.00038 | $0.00727 |
| Sonnet 5.5 | $0.00019 | $0.00363 |
| Haiku 4.5 | $0.00010 | $0.00182 |
Grade A, and why
visualize 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 17d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visualize
render_visual 把一段 HTML 渲染成回复里的交互图。它不在常驻工具里:先用 load_tools 传入插件工具目录中
visuals 的准确 ID(形如 visuals@release)取得 schema,再用 tool_call 传入 name: "render_visual" 和参数调用。
什么时候画
图要替用户省力:扫一眼就能得到读一段话才能得到的东西,才值得画。
适合画:两个以上的数要比大小、看排名或占比;一组数随时间变化;流程、步骤、因果链; 东西里面套着东西的结构;靠空间位置才讲得清的原理;"如果把 X 调大会怎样"。
不要画:答案是一个数、一句话或几条短列表;用户要代码、原文、清单或纯文字; 没有真实数据(不为数据图编数);话题沉重(疾病、死亡、灾难、冲突、个人困境)时只在确实帮助理解时画, 样式平实,不玩修辞。拿不准就先用文字回答,再问要不要画。
按意图选形式
先问用户想查阅还是想理解:查阅要一张准确的地图,理解要一个对的心智模型。 同一个主题,问法不同,图就不同——看动词,不看名词:
| 用户在问 | 形式 | 画什么 |
|---|---|---|
| 一两个关键数 | 指标 | hero 数字或指标卡,不画图 |
| 比较、排名、趋势、构成、两量关系 | 数据图 | ak 图表,见 charts.md |
| "流程是怎样的""经过哪些步骤" | 流程图 | 方框加箭头,见 diagrams.md |
| "由哪些部分组成""架构是什么" | 结构图 | 容器套区域,见 diagrams.md |
| "它是怎么运作的""为什么会这样" | 机制示意 | 画机制本身,能操作就加控件,见 diagrams.md |
| "调大会怎样""帮我算算" | 交互讲解 | 滑块加实时读数和图,见 interactive.md |
| "这几个选哪个" | 对比卡片 | 每个选项一张卡,见 interactive.md |
内容是解释性的就用编辑式版式(无外框,留白即容器);内容是一个有边界的对象(一张名片、一张收据)就用一张卡片包住。
复杂度预算
- 一张图只讲一件事。方框里只写名称,最多八九个字,解释写在正文。
- 一行最多四个方框;用户一口气列了六个以上组件,先画只有方框的总览,再每个子流程单独一张图。
- 颜色最多两种强调色加中性色;颜色表达含义时加一行图例。数据图最多四个系列,再多就并入"其他"。
- 正文里写了"点开看细节",图本身就必须真的精简。
调用顺序
- 按形式读对应写法(路径相对本技能目录),只读用得上的:
charts.md、diagrams.md、interactive.md; - 先用文字讲直觉或结论,再调用
render_visual。解释、标题和总结都写在正文里,图里只放图; 示意图、多元素布局这类坐标容易出错的图,先加draft: true打草稿(见下节),简单的数据图直接发布; - 主题复杂就拆成几张图,按顺序讲;两张图之间写一两句话衔接,说了几张就真的画几张;
- 成功后接着说图里该看什么,不复述图里已有的数字和标签;
- 每一步最多并行两次调用。
先打草稿,再发布
正式调用一次,用户就看到一张图;发布之后再为外观重画,用户会看到两张。所以外观问题在发布之前解决:
- 带
draft: true调用:照常渲染并回传 720px 宽的截图,但不展示给用户; - 能看图时逐项检查:文字和文字、文字和线条有没有重叠;标签有没有被截断或超出边界; 箭头有没有穿过不相干的方框;留白是否失衡;颜色和图例是否对得上;
- 有问题就改完整 HTML 再打一次草稿,草稿最多三次;没问题就省略
draft,用同样的参数正式发布; - 正式发布的结果也带截图,这时只为脚本报错这类真正坏掉的情况重画; 只是"可以更好看"不算问题。
结果里写着当前模型不接收图片时,草稿看不到效果,以后直接发布。
渲染报错、空白、横向溢出、出现 NaN 时,草稿和正式调用都会直接失败并返回原因,图不会展示,按原因改完再调用即可。
通用规则
html是 body 片段,可含内联 style、script、SVG、Canvas;不依赖网络、外部库、宿主 API、iframe、 表单提交或导航,也不放外链。最多 200,000 个字符。- 无缝:背景透明,不加外框和底色,不重复正文标题,看起来像聊天的一部分。
- 扁平:不用渐变、阴影、模糊、发光和装饰纹理;不用 emoji,图标用简单的 SVG 形状。
- 宽度:适应 280px 与 720px,不横向溢出;网格列写
minmax(0, 1fr),宽表格用table-layout: fixed。 - 颜色只用主题 token,深浅色自动适配,不写死 #333 这类颜色:文字
--ak-color-text-primary/secondary/muted, 线条--ak-color-border-default/strong,底面--ak-color-bg-canvas/surface,强调--ak-color-action-primary, 系列--k1…--k6、--k-gray、--k-hot。想象背景变成近黑色,每段文字是否还读得清。 只有描绘真实物体颜色(天空、水、皮肤)时才写死颜色,并整组写死。 - 字体:图里的文字用
--ak-type-ui,最小 12px;只用常规和加粗两种字重;不用全大写,不在句中加粗。 - 圆角:控件 8px,卡片 12px;只有单侧边框时不加圆角。
- 不用
position: fixed、全屏 API 和内部滚动区;高度由内容撑开。 - 显示出来的每个数都要取整(
toFixed、Math.round或Intl.NumberFormat),滑块设好step。 - 无障碍:HTML 图以
<h2 class="sr-only">开头写一句话概括;独立 SVG 加role="img",第一个子元素是<title>和<desc>。
What ships with it
3 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.
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.
- 17d ago First seen · 87 lines · 95 tokens per session scan A 87955d054f08
visualize is a skill published in the GitHub repository kachofugetsu09/akashic-agent (518 stars, last pushed today), licensed MIT. It adds 95 tokens to every session and 1,817 once invoked, about $0.0004 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 2026-10-21.
visualize compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| visualizekachofugetsu09/akashic-agent | Skill | 518 | today | MIT | A | 95 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |