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-video-prompt-governancegit 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-video-prompt-governance)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/tapcanvas-video-prompt-governance"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-video-prompt-governance/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-video-prompt-governance"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/tapcanvas-video-prompt-governance.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 | $0.00112 | $0.01965 |
| Opus 5.5 | $0.00045 | $0.00786 |
| Sonnet 5.5 | $0.00022 | $0.00393 |
| Haiku 4.5 | $0.00011 | $0.00197 |
Grade A, and why
tapcanvas-video-prompt-governance 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 3d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TapCanvas 视频提示词合同治理
目标
维护一份权威 authoring contract,让 writer 与 reviewer 读取同一维度、同一 owner 和同一版本。领域 Skill 负责提供方法,不再复制“最终提示词标准”;Hono/Web 只做确定性协议校验,不接管语义质量。
权威合同固定在:
apps/agents-cli/skills/tapcanvas-video-prompt-writer/references/authoring-contract-v1.json
开始治理前完整读取权威合同 reference。修改正式 writer 或 reviewer 时,先读取两者骨架,再按本次变更涉及的 dimension、字段与复盘项精确读取对应标题单元;涉及整体生产范围时再按阶段读取 tapcanvas-video-workflow 的对应标题单元。禁止为了“完整”把三份大型 Skill 全文常驻到同一模型窗口。
知识拆解
把每条新知识先原子化为:
{
"claimId": "稳定 ID",
"source": "skill、用户反馈、真实 run 或外部方法来源",
"evidence": "可追溯证据",
"appliesTo": "跨题材、特定题材、特定模型或仅展示",
"proposal": "它要求 authoring 改变什么"
}
再只允许归入以下一类:
universal_contract_upgrade:跨题材、跨模型成立,现有维度无法完整表达;才允许升级合同版本。domain_extension:只适用于战斗、文戏、TVC、情绪、转场等领域;映射到现有dimensionId,放 writer reference 或对应领域 Skill,不扩核心字段。provider_fact:时长、分辨率、引用数、原生音频等能力;只由实时generationContract提供,禁止写死进 authoring contract。presentation_projection:13 列表、UI 卡片、日志标签等展示形式;由 renderer/UI 投影,不改变 writer JSON。non_blocking_heuristic:案例经验、审美倾向、推荐词汇;可参与 agent 复盘,但不形成最低字数、评分、关键词或运行时门禁。conflict_or_reject:与用户事实、动态模型合同、付费幂等、真实资产或现行权威合同冲突;记录冲突,不静默合并。
映射与升级规则
- 优先映射现有
dimensions[].id。只有无法表达跨题材必要信息时,才提议新增维度或字段。 - writer 输出字段和 reviewer 检查项都引用同一个
dimensionId;reviewer 不重抄第二份规范,也不依赖退役 Skill。 - 通用合同只定义信息维度、owner、字段落点和复盘问题,不规定题材答案。战斗力度、文戏克制、TVC 卖点等留在领域 extension。
- 用户本轮事实与真实项目状态优先;动态 generationContract 管供应商硬边界;authoring contract 管创作信息结构;领域 extension 管方法;heuristic 只作建议。
- 用户明确指定的节奏、密度、收束和结果边界优先于所有默认叙事模板。钩子、悬念、余波、呼吸点、高潮前抽空、收束或未决结果都必须有用户或权威来源依据;没有依据时,结构字段应明确表达“不适用”(例如可空字段使用
null),不得为了填满模板而杜撰。 - 创作复盘发生在 writer 同一执行链并直接修订首稿。合同与 reviewer 都不得成为 Hono/Web 的语义质量门禁,也不得拦截、回滚或丢弃已受理媒体。
- 版本升级只允许显式
major/minor/patch:删字段或改 owner 为 major,新增可选维度为 minor,措辞澄清与 consumer 修复为 patch。 temporalFrameTrack + temporalFrameCoverage是 1.3.0 的通用合同升级:它把“信息密度”定义为每个不超过 1 秒时间窗的起帧、可见过渡、承帧与真实镜头映射,不把视频模型内部实现臆测成供应商事实,也不把该规则转换为字符数、固定 shot 数、关键词或 Hono/Web 语义评分门禁。
交付格式
先输出并审查变更提案,再修改文件:
{
"baseContract": "tapcanvas/[email protected]",
"claims": [],
"mappings": [
{
"claimId": "claim-id",
"classification": "domain_extension",
"dimensionIds": ["action_causality_physics"],
"targetFiles": [],
"reason": "为何不升级核心合同"
}
],
"contractChanges": [],
"writerChanges": [],
"reviewerChanges": [],
"conflicts": [],
"evalCases": []
}
What ships with it
8 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.
- agents/openai.yaml 330 B
- references/critical-path-contract-proposal-2026-08-25.json 8.5 KB
- references/impact-frame-conflict-proposal-2026-10-16.json 9.7 KB
- references/linear-state-continuity-proposal-2026-10-19.json 6.3 KB
- references/manju-laoli-skill-review-2026-08-28.json 4.9 KB
- references/source-prompt-material-coverage-2026-08-28.json 1.5 KB
- references/source-prompt-material-review-2026-08-28.json 8.4 KB
- scripts/audit-contract-consistency.mjs 6.1 KB runs code
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.
- 3d ago Changed a4059ffef4f6
- 1mo ago First seen · 107 lines · 112 tokens per session scan A c722e9f750b0
tapcanvas-video-prompt-governance is a skill published in the GitHub repository anymouschina/TapCanvas (712 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 1,965 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 2026-09-21.
tapcanvas-video-prompt-governance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tapcanvas-video-prompt-governanceanymouschina/TapCanvas | Skill | 712 | 4d ago | MIT | A | 112 | Codex |
| dramakexixihhhh/ai-short-drama-skill | Skill | 88 | 2mo ago | MIT | A | 279 | Claude Code, Codex |
| last30Dayschaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 83 | Claude Code |
| thisWeekchaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 77 | Claude Code |
| short-drama-storyboardzenstory-ai/drama-skills | Skill | 3.9k | today | MIT | A | 102 | Codex |
| md-fetch-summarizechaitanyagiri/munder-difflin | Skill | 9.3k | 6d ago | MIT | A | 93 | Claude Code |
| social-postHao0321/claude-skill-social-post | Skill | 750 | 22d ago | MIT | A | 119 | Codex |