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 anymouschina/TapCanvas --skill tapcanvas-scene-cardgit clone --depth 1 https://github.com/anymouschina/TapCanvasWrote 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/anymouschina/tapcanvas/tapcanvas-scene-card)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-scene-card"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-scene-card/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/anymouschina/tapcanvas/tapcanvas-scene-card"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-scene-card.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 | $0.00171 | $0.05493 |
| Opus 5.5 | $0.00068 | $0.02197 |
| Sonnet 5.5 | $0.00034 | $0.01099 |
| Haiku 4.5 | $0.00017 | $0.00549 |
Grade A, and why
tapcanvas-scene-card 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 1mo 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TapCanvas Scene Card
唯一职责
本 Skill 是场景视觉身份、空间设计和场景灯光的唯一方法论来源。其他 Skill 可以识别“需要哪些场景”、提供剧情、时代、人物调度和状态事实，但不得另写场景卡模板、灯光情绪查表、固定 prompt 前后缀、默认模型或 URL 复用规则。
场景卡是无人、可复用的纯空间生产资产；空景仍必须具有明确的叙事功能，不能只有“地点名 + 电影感 + 超高清”。它必须同时完成：
- 空间身份：换机位后仍能认出同一地点；
- 叙事功能：空间结构确实允许本场戏发生；
- 材质生态：建造、使用、维护、损耗和气候留下互相解释的痕迹；
- 灯光因果：每束主要光都有来源、方向和作用对象；
- 连续性：日夜、天气、实用灯、破坏状态与上一版有可追溯关系；
- 可执行资产：落为真实图片节点/素材版本和稳定 ID，供分镜、关键帧与视频复用。
资产类型
sceneAssetRole |
用途 | 生成方式 |
|---|---|---|
space_anchor |
canonical 空间身份；锁定拓扑、尺度、入口、地标、材质和基准灯光 | 首次建立场景或用户明确重建 |
lighting_variant |
空间不变，只改变可证明的时段、天气、灯具状态或叙事光相 | 必须引用精确 space_anchor node/material/version ID，以图生图派生 |
state_variant |
灾损、布置、季节、占用方式等可见场景状态发生变化 | 引用基态或上一状态的精确 ID，只改差量 |
同一变化同时涉及光与物理状态时仍只建一个 variant，并在 visualStateFacts 与 sceneLightingSpec 中分别记录，禁止同一画面创建两套竞争版本。
拓扑图与站位图视觉范式（2026-09-14）
后续拓扑图与站位图的提示词编译必须先读取 正交建筑剖切与动作调度模板，以用户提供的 奶茶店原文 为绘制范式。固定要求为严格 90° 正交顶视、参考空间还原、精细材质、16:9、清晰双语标注与有事实依据的动作/机位关系；场景名称、人物、道具、标语和动作只来自当前任务。该技术图的展示要求优先于下文普通场景卡的非固定画幅/照明建议，且不改变无人空间锚的职责。
证据层级
站位/拓扑图默认先生成本场景的无人正交俯视底图，再按结构化坐标叠加角色、走位、机位与轴线。底图保持场景身份、材质和光源；门墙与固定地标服从同一归一化坐标基准，不把透视照片直接当作俯视底图。同一布局/状态可复用一张图，布局变化以新资产表达。
已有场景图时以精确 node/asset ID 图生图派生；没有现成图时依据已确认空间事实原创，不伪称有图片来源。Workflow BeatSheet 的 blockingPlans[].backgroundPlan 提交 assetId/displayName/prompt/negativePrompt/referenceAssetBindings，独立底图集合负责真实生成，不混入视频参考池。独立工具通过 backgroundNodeId 消费底图；给旧图新增版本时同时提交 sourceDiagramNodeId，保留旧图和下游引用。禁止传图片 URL。
按以下顺序读取：
- 用户本轮明确要求；
- 当前章节/剧本/BeatSheet 的地点、时间、天气、事件和调度事实；
- 已确认的 style lock、场景素材及精确版本；
- 上一场景状态与当前项目真实状态；
- 为可拍性所需的最小自由设计。
内部把设计分成：
confirmedFacts：来源明确，不得改写；designInferences：从功能、时代、气候、经济与人物使用方式推导；freeDesign：证据未覆盖时的原创选择，必须与前两层相容。
不得把推断伪装成原文，不得用通用“古风房间 / 赛博街道 / 豪华办公室”母版代替证据。
工作流
1. 读取并验真
需要读取或操作真实项目、画布、节点与素材库时，只通过 tapcanvas-api。场景复用只接受可验真的当前画布 node ID、material asset ID 或精确 version ID；URL、label、prompt、坐标、连线和“看起来像同一个地方”都不能作为 canonical 身份。
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.
- 1mo ago First seen · 246 lines · 171 tokens per session scan A 59ec69fac2e0
tapcanvas-scene-card is a skill published in the GitHub repository anymouschina/TapCanvas (686 stars, last pushed today), licensed MIT. It adds 171 tokens to every session and 5,493 once invoked, about $0.0007 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 2026-09-21.
Other skills, from other repositories
dotcanvas
Author and edit a Grida .canvas board — a .canvas.json manifest plus document files (references, generated images, notes) placed on an infinite canvas. Use when working on a .canvas bundle or arranging visuals/design work spatially. For a linear deck/presentation, use the slides skill instead.
slides
Build a Grida slides deck — a .canvas bundle in slides mode whose pages are SVG documents (16:9, one SVG per slide). Use when creating a presentation, pitch deck, slideshow, or talk.
svg
Author and edit .svg files in a Grida editor session — live-canvas binding, SVG output style, and parse-error recovery. Use when creating or modifying an SVG document.
penecho-canvas
A skill for creating diagrams, interactive previews, and visual explanations on PenEcho Cloud canvases. It can also revise existing canvases using the user's handwriting and annotations.
design-skill
Use BEFORE building or restyling anything a user will see — web/mobile UIs, landing pages, dashboards, components, emails, AND creative work like Three.js/WebGL/canvas/SVG scenes, data-viz, games, and animations — to make it look intentional and polished, not generic; covers tokens, type, color, layout, motion…
penecho-mcp
Create, read, or edit PenEcho canvases, including following the user's drawings and notes.