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 huangwb8/skills --skill auto-draw-plotgit clone --depth 1 https://github.com/huangwb8/skillsWrote 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/huangwb8/skills/auto-draw-plot)<a href="https://agentmods.dev/skills/huangwb8/skills/auto-draw-plot"><img src="https://agentmods.dev/badge/skills/huangwb8/skills/auto-draw-plot/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/huangwb8/skills/auto-draw-plot"><img src="https://agentmods.dev/badge/skills/huangwb8/skills/auto-draw-plot.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 | $0.00108 | $0.05287 |
| Opus 5.5 | $0.00043 | $0.02115 |
| Sonnet 5.5 | $0.00022 | $0.01057 |
| Haiku 4.5 | $0.00011 | $0.00529 |
Grade B, and why
auto-draw-plot scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `api_config`(可选):Codex 本机配置优先使用 `~/.codex/config.toml` 中当前 BenszAPI provider 的 `base_url` 与 `experimental_bearer_token`;`~/.codex/auth.json` 仅作为兼容认证来源,`~/.bensz-skills/config/remote.env` 只作为缺失字段的兜底。默认 `auto` 只在运行前按优先级选 How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Draw Plot
目标
- 以用户需求为起点,由宿主 AI 进行语义规划,再构造适用于当前图片 provider 的 prompt,通过 BenszAPI 直接完成“parallel-vibe 规划留痕 → prompt → 出图 → 视觉评估 → 继续/停止”的闭环;脚本默认不调用额外 Gemini 文本接口。
- 触发边界:默认模式是
general;用户明确要技术路线图/roadmap/flowchart 时使用roadmap,明确要原理图/机制图/架构图时使用schematic。后续新增类型应作为config.yaml:modes.presets扩展,不改主流程。 parallel-vibe是必选工作流的一部分,不是可选增强;默认通过scripts/run_draw_plot.py在独立隐藏工作区里完成整个闭环。auto-draw-plot独立负责需求拆解、prompt 生成、图片 generation/edit、多轮保真微调、评估与交付;图片请求由本 skill 的脚本通过 BenszAPI 提交,不调用也不依赖imagegenskill。完整的imagegen技能边界见「Skill 专属约束」。
流程
输入
user_need(必需):自然语言描述的图像需求、输出用途、必要的视觉语义与格式要求。mode(可选):general/roadmap/schematic;默认general。模式只改变 prompt preset、默认画布和评估口径,不引入 legacy draw.io 渲染器。三种模式的语义与文字策略:general:通用绘图模式,适合普通信息图、封面图、概念图和自由描述。roadmap:技术路线图模式,强调 3-5 阶段、阶段标题条、主链箭头、风险/备选虚线、A4 打印可读。schematic:原理图/机制图模式,强调分组大框、圆角节点、机制链/模块关系、主链与辅助箭头分层。roadmap/schematic的文字策略:优先把标签自然换成 2-3 行,也不要横向压缩字形;默认使用现代黑体/思源黑体/Noto Sans CJK 风格的正常字宽、常规到半粗体。除非用户明确要求窄体标题或压缩排版,否则禁止窄体、长体、压缩体、condensed/narrow/compressed font、横向压缩和瘦长拉伸字体。- 不要把
roadmap/schematic回退成 draw.io、SVG/PDF 或 TEX 强绑定流程;这些 legacy 能力只作为 prompt 和评估经验迁移。
api_config(可选):Codex 本机配置优先使用~/.codex/config.toml中当前 BenszAPI provider 的base_url与experimental_bearer_token;~/.codex/auth.json仅作为兼容认证来源,~/.bensz-skills/config/remote.env只作为缺失字段的兜底。默认auto只在运行前按优先级选择连接与鉴权检查通过的 provider,真实生成资格以 Images submit 响应为准。image_provider(可选):用户明确指定的图片模型/provider,如gpt-image-2.5-flare、gpt-image-2.5-sunburst、gpt-image-2或nano_banana。显式指定后必须只用该 provider/model,失败时暂停并报告原因,不得切换到其他模型。allow_provider_fallback(可选):只有用户明确说“失败可以换模型/可以回退到另一个 provider”时才为 true;该授权仅覆盖已确认未创建任务的 provider 故障,不覆盖订阅、余额、权限、overage、计费服务错误或 submit 空/非 JSON 等任务创建状态不确定的协议错误。max_rounds(可选):最大优化轮数,默认 3;若用户另有指定,以用户为准。visual_constraints(可选):比例、期望布局、色调、字体等硬约束。尺寸只作为 provider 原生尺寸选择参考,不承诺最终导出像素。quality/provider_size/output_format/output_compression(可选):OpenAI 图片模型显式 provider 参数;默认模型为gpt-image-2.5-flare,默认参数分别为low、1024x1024、jpeg、85,均执行白名单或范围校验。reference_images(可选):用于 prompt 引导的风格/布局图;第 2 轮起上一轮output.jpg会自动作为第一参考图,用户参考图排在其后。workspace_base(可选):用户显式指定的隐藏工作区根目录;未指定时使用当前目录.bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-draw-plot/。
What ships with it
17 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.
- CHANGELOG.md 11 KB
- config.yaml 9.5 KB
- README.md 16 KB
- references/parallel-plan.md 1.5 KB
- references/prompt-guidelines.md 3.3 KB
- scripts/build_parallel_plan.py 2.8 KB runs code
- scripts/common.py 4.5 KB runs code
- scripts/env_utils.py 3.0 KB runs code
- scripts/evaluate_image.py 9.6 KB runs code
- scripts/generate_image.py 9.9 KB runs code
- scripts/image_provider_client.py 81 KB runs code
- scripts/init_workspace.py 7.3 KB runs code
- scripts/modes.py 3.9 KB runs code
- scripts/nano_banana_check.py 1.1 KB runs code
- scripts/nano_banana_client.py 17 KB runs code
- scripts/parallel_round_worker.py 1.9 KB runs code
- scripts/run_draw_plot.py 25 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.
- 1mo ago Changed · +21 tokens per session 7db5bc4416d9
- 1mo ago Changed · -20 lines a9ca62e54b1f
- 1mo ago Changed · +30 lines 094267b79bd5
- 1mo ago First seen · 120 lines · 87 tokens per session scan B 8f6feef871fe
auto-draw-plot is a skill published in the GitHub repository huangwb8/skills (50 stars, last pushed 10d ago), licensed MIT. It adds 108 tokens to every session and 5,287 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
design-dna
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides…
design-system-synthesizer
Use when the user says 'build a design system for my site', 'extract design tokens', 'capture my brand', or 'build my style guide', or after a rebrand. Reads representative pages, theme files, and media to extract logo, colors, typography, spacing, and components, then writes a visible style-guide page.
art-direction
Use on any page build, redesign, or 'make it look better' request on a site that has (or needs) a saved Art Direction. Loads the direction before the first element is written, plans tokens in two passes against the direction's donts and the known AI-default aesthetics, builds with tokens preserved, checks the result…
page-template-library
Use when the user says 'save this as a template', 'create a playbook from this page', 'capture this layout', or has hand-built the same page type three times. Captures canonical page patterns as reusable playbooks that later page generation can spawn from in seconds.