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 mythkiven/figma-ios-codegen --skill figma-ios-comments-integrationgit clone --depth 1 https://github.com/mythkiven/figma-ios-codegenWrote 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/mythkiven/figma-ios-codegen/figma-ios-comments-integration)<a href="https://agentmods.dev/skills/mythkiven/figma-ios-codegen/figma-ios-comments-integration"><img src="https://agentmods.dev/badge/skills/mythkiven/figma-ios-codegen/figma-ios-comments-integration.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 | $0.00068 | $0.01186 |
| Opus 5 | $0.00034 | $0.00593 |
| Sonnet 5 | $0.00014 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
figma-ios-comments-integration 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 8d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Figma 评论集成（消费数据包）
阶段 2 不再获取或匹配评论。figma-ios-preload-data 已经在阶段 1 完成了：
- 拉取所有评论
- 解析 message → tags（iconfont / icon_correction / color / color_correction / rotation / 自由文本）
- 命中节点（坐标 hit-test + 关键词 boost + iconfont 祖先重定向）
- 给出 confidence +
is_safe - iconfont 修正已被脚本主动应用：
parsed.iconfont_name在confidence>=medium且is_safe时已覆盖nodes[best_node_id].iconfont.symbol，并标source=comment+original_symbol。阶段 2 直接读iconfont.symbol即可，不需要再二次比对。 - 颜色评论不会改写
design.json：parsed.color只在comments.json；生成时由 figma-ios-design-token-mapping 优先于节点fills[].color。
数据来源
| 文件 | 字段 |
|---|---|
{data_dir}/comments.json |
comments[comment_id] |
{data_dir}/design.json |
nodes[node_id].comments = [comment_id, ...]（反向索引） |
comments.json 字段速查
{
"comments": {
"1693773932": {
"id": "1693773932",
"message": "这个是iconfont：icon_next_12",
"user": "岩竹",
"created_at": "2026-03-26T10:30:00Z",
"resolved": false,
"parsed": {
"tags": ["iconfont", "icon_correction"],
"iconfont_name": "icon_next_12",
"color": null
},
"is_safe": true,
"match": {
"best_node_id": "I1:343;1:342;30:8689",
"confidence": "high",
"candidates": [
{"node_id": "...", "score": 50.0, "reasons": ["bbox_hit","iconfont_keyword_boost"]}
]
}
}
}
}
字段是
resolved: bool（由 Figmaresolved_at推导），没有resolved_at字符串字段。
处置规则
| confidence | 处置 |
|---|---|
high |
应用（iconfont 已在 design；颜色按 token-mapping 读评论） |
medium |
应用，并在生成代码注释中标注「评论建议（confidence=medium，作者=xxx）」 |
low |
不应用，但在生成的 README "待人工确认" 列表中列出原文 |
unmatched（无 best_node_id） |
同 low |
已 resolved 的评论（resolved == true）忽略。is_safe == false 的评论不应用（阶段 1 也不会回写 iconfont）。
覆盖规则（按 tag）
| tag | 阶段 1 | 阶段 2 |
|---|---|---|
iconfont / icon_correction |
已写入 node.iconfont.symbol |
直接读 iconfont.symbol，查 iconfont_map.json |
color / color_correction |
不改 design.json；parsed.color 留在评论 |
映射时优先 parsed.color，再回退节点 fills[].color（TEXT 也是 fills，无 text.color） |
| rotation 相关 | — | 见 iconfont-mapping；评论禁止旋转则忽略 iconfont.rotation |
| 自由文本 | — | 不覆盖字段，仅 // 评论：xxx |
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.
- 8d ago First seen · 95 lines · 68 tokens per session scan A 788556b0348c
figma-ios-comments-integration is a skill published in the GitHub repository mythkiven/figma-ios-codegen (9 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,186 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
figma-codegen
Generate framework-aware code from a Figma design. Reads the project's stack profile and emits code matching the existing framework (React/Vue/Svelte/Next/etc.) and styling (Tailwind/CSS/CSS-in-JS), reusing existing components and design tokens instead of regenerating from scratch. Triggers whenever the user wants a…
figma-build
Build a Figma design from code or a description — the reverse of figma-codegen. Reuses the connected file's existing design system (components, variables, styles) instead of drawing primitives with hardcoded values. Triggers whenever the user wants something created or updated IN Figma from code or a spec — e.g.…
unship
Compare agent-made local alternatives in the real app: UI, copy, states, small flows, design-system treatments, rendered docs or DX previews. Use for Unship setup, Canvas comparisons, selection, and cleanup.
flato-design-mcp-guide
Use when creating, editing, inspecting, exporting, or troubleshooting Flato designs through Flato Design MCP tools such as flatowhoami, flatogetdesigncontext, flatocreatepages, flatoupdatepages, flatoupdatecanvas, and flatoexport.
create-workflow-diagram
Create FigJam/Miro-style workflow diagrams as high-quality PNG images from plain-text workflow descriptions. Renders beautiful HTML diagrams with connected nodes, arrows, and labels, then screenshots them for sharing.
create-chatgpt-mockup
Render pixel-accurate ChatGPT mobile (iOS) screen mockups in light mode from a thread JSON. Supports user text bubbles, user image attachments, assistant markdown prose, citation chips, the OpenAI spiral logo, the Apps-SDK GPT chip in the composer, and three header styles (model-tag, plain title, "Get Plus"). Fixed…