tapcanvas-prop-card

tapcanvas-prop-card is a skill for Claude Code, Codex from anymouschina/TapCanvas. It costs 124 tokens per session (3,058 once invoked), scanned A, original, MIT.

A visual-asset skill for creating reusable cards that define a prop such as a weapon, tool, or important object. It records the object's stable identity, parts, usable features, and visible condition changes, then places the result on a TapCanvas canvas.

In plain words
What is it for?
Use it to create, complete, rebuild, batch-create, or derive reusable prop assets, including damaged, opened, dirty, missing-part, or charged versions.
Why use it?
It prevents the same object from changing shape, materials, or parts between camera views and later scenes. It also keeps temporary poses, effects, and background decoration from being mistaken for the object's core design.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Good fit Use it to create, complete, rebuild, batch-create, or derive reusable prop assets, including damaged, opened, dirty, missing-part, or charged versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anymouschina/tapcanvas/tapcanvas-prop-card
Install

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.

Any agent
npx skills add anymouschina/TapCanvas --skill tapcanvas-prop-card
Clone the repo
git clone --depth 1 https://github.com/anymouschina/TapCanvas

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for tapcanvas-prop-card

README.md
[![agentmods](https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-prop-card/github.svg)](https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-prop-card)
Your own site
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-prop-card"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-prop-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.

agentmods 80×15 button for tapcanvas-prop-card

Your own site · 80×15
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-prop-card"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-prop-card.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00124 $0.03058
Opus 5.5 $0.00050 $0.01223
Sonnet 5.5 $0.00025 $0.00612
Haiku 4.5 $0.00012 $0.00306

Measured 1mo ago against content hash de738c9ac69c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tapcanvas-prop-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.

apps/agents-cli/skills/tapcanvas-prop-card/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TapCanvas Prop Card

唯一职责

本 Skill 是 canonical 道具身份、可交互结构和状态版本的唯一方法论。目标不是生成一张“高级感产品照”,而是建立后续分镜、关键帧和视频可以稳定复用的物体资产:同一物体换机位仍能识别,抓握、开合、装配、受力和状态变化不会凭镜头重置。

角色身上的固定身份配饰若主要用于识别人,留在 tapcanvas-character-card;固定建筑、门窗、柜台和不可移动重型陈设若主要定义空间,留在 tapcanvas-scene-card。只有会被拿取、交接、操作、损坏、变形、追踪或独立复用的剧情物体进入本 Skill。一次性无剧情功能的环境纹理不建道具卡。

成功标准

  • 身份稳定:轮廓、比例、部件关系、主材质与不可变标记跨视图一致。
  • 功能可演:持握点、支撑点、受力路径、开合/装配关系和可动部件来自来源事实或明确设计判断。
  • 状态可追溯:基态与损坏、展开、污染、缺件、充能等状态分层;状态版引用精确 canonical asset,只写差量。
  • 职责隔离:布局、风格、身份与内容参考各自使用明确绑定;参考图不替代当前镜头动作。
  • 资产真实:用户要真实道具卡时,必须有真实 node/task/status 或既有素材版本证据;文本计划和 URL 口述不算交付。

审美复盘只驱动当前 agent 同链修订,不形成 Hono/Web 的关键词、最低字数、评分或生成门禁。供应商已受理或已生成的资产必须保留,问题以诊断和新版本追加。

资产职责

propAssetRole 用途 身份规则
identity_anchor 锁定 canonical 基态道具 materialIdentity.mode="base",使用 prop-card/v1
state_variant 锁定损坏、展开、污染、缺件、充能等可见状态 materialIdentity.mode="state",引用精确 canonicalAssetId

纯姿态图或人物持物关系图不是道具身份卡;它们消费道具卡和角色卡,不得反向改写道具结构。剧情现场的偶然落点、手势、火花、血迹或光色也不能焊进基态。

输入与证据

按以下顺序读取并保留来源层级:

  1. 用户本轮明确指定、用户提供的参考资产及其职责;
  2. 正文、剧本、BeatSheet、对象合同和已确认 story facts;
  3. 当前项目已确认的道具基态/状态版本、角色卡、场景卡与 style lock;
  4. 为可视化与物理可执行性所需的 agent 设计判断。

内部把信息分为 confirmedFacts、designInferences 与 freeDesign。尺寸、内部结构、隐藏机关、材质、所有权与能力没有来源时不得伪装成原文事实;用户允许原创时可以做有理由的设计选择,并明确其属于设计判断。

涉及读取、生成、轮询或写入真实画布时,先加载 tapcanvas-api,只通过其公开合同执行。模型上下文只传 node ID、asset ID、version ID 和结构化 descriptor,不复制内部图片 URL。

工作流

1. 读取并验真现有资产

  • 确认 canonical propName、当前故事作用域和状态。
  • 优先复用匹配的 referenceType="prop" + propName + propProfileVersion="prop-card/v1" 已确认资产。
  • 基态还必须携带 materialIdentity={mode:"base",canonicalName:propName};状态版必须携带同名 canonicalName、精确 canonicalAssetId、stateKey 与 stateDescription。
  • 裸 label、prompt、坐标、连线、URL 和“看起来像同一件”都不能证明 canonical 身份。

2. 建立道具因果核

写外观前先回答:

  • 它在剧情中承担什么不可替代的功能,谁会操作、携带或识别它?
  • 它的前/后、上/下、左/右如何由可见结构辨认?
  • 正常使用时从哪里握持、支撑、开启、装配、承重或施力?
  • 哪些部件能动、能拆、能变形;哪些必须永久保持相对位置?
  • 材质和磨损如何由制造、使用、维护、气候与事件解释?
  • 哪些变化属于当前状态,哪些属于跨镜稳定身份?

不要用“神秘、精致、古朴、科技感、电影级”代替几何、材料和功能。只有故事确实需要内部机构时才设计机构;普通杯子、信件、钥匙不强制 X 光或机械剖面。

Read the full file on GitHub · 189 lines

Files

What ships with it

2 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.

Changes

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.

  1. 1mo ago First seen · 189 lines · 124 tokens per session scan A de738c9ac69c

Subscribe to this mod's changes

tapcanvas-prop-card is a skill published in the GitHub repository anymouschina/TapCanvas (686 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 3,058 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

dramake

A production workflow for turning an idea, story, script, storyboard, or existing footage into a short AI drama or film. It covers planning, generation, voice, editing, and quality checks for formats such as vertical and horizontal video.

xixihhhh/ai-short-drama-skill · 279 tokens

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens

short-drama-storyboard

A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.

zenstory-ai/drama-skills · 102 tokens

md-fetch-summarize

Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…

chaitanyagiri/munder-difflin · 93 tokens

social-post

A workflow for planning, writing, publishing, and evaluating social-media posts in the user's established voice. It covers Facebook, Instagram, YouTube, Threads, and X, including selected comment operations.

Hao0321/claude-skill-social-post · 119 tokens