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 LZheng0411/Lzheng-fitness --skill lzheng-fitness-workbench-buildergit clone --depth 1 https://github.com/LZheng0411/Lzheng-fitnessWrote 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/lzheng0411/lzheng-fitness/lzheng-fitness-workbench-builder)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-fitness-workbench-builder"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-fitness-workbench-builder/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/lzheng0411/lzheng-fitness/lzheng-fitness-workbench-builder"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-fitness-workbench-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00148 | $0.03917 |
| Opus 5 | $0.00074 | $0.01959 |
| Sonnet 5 | $0.00030 | $0.00783 |
| Haiku 4.5 | $0.00015 | $0.00392 |
Grade A, and why
lzheng-fitness-workbench-builder 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 yesterday.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lzheng 健身工作台构建器
把工作台视为“唯一固定界面模板 + 用户事实文件 + 可重复构建脚本”。唯一视图资产是 assets/workbench-template.html；AI 只能刷新 workbench-data，不得手写另一套工作台。不把训练重量写死在页面视图，不复制其他人的个人记录。工作台必须适配增肌、减脂、力量和综合健身，四个力量主项只属于力量模式，不能作为其他目标的前提。
读取 ../lzheng-training-system/references/system-contract.md；如果存在交接记录，读取 ../lzheng-training-system/references/handoff-schema.md，只消费其中已确认产物。系统根目录优先使用本次用户指定路径，其次使用套件配置；视图代码不得包含固定磁盘路径。
低 token 读取边界
日常计划修改、复盘和本地刷新禁止把整份 健身工作台.html 或 assets/workbench-template.html 读入 Agent 上下文。先运行：
python "<skill>/scripts/Inspect-FitnessWorkbench.py" --project "<项目根目录>"
该命令只输出模板完整性、当前计划、今日/下次训练、同步状态和本轮应读主源。随后只读取 authoritative_sources 中与当前任务有关的 JSON/Markdown；不要扫描历史计划、完整复盘目录、全部专家库或构建器源码。视觉开发、模板修复及检查器报出结构损坏时，才允许定点读取模板命中行；仍不得默认全量读取 100 KB 以上 HTML。
先判断任务
-
侧栏缺失 / 已有页面升级：读取 界面升级，先检查实际运行模板和原 HTML，再使用独立
upgrade-workbench-ui。用户已经要求修复时直接完成兼容检查、备份、升级与浏览器验收；未知自定义不能静默覆盖。数据刷新和重新安装 Skill 都不能替代界面升级。 -
从零构建 / 新电脑迁移：读取 输入契约，使用初始化脚本创建完整目录和可运行页面。
-
刷新数据：保留正式 HTML 视图，只运行数据生成器更新唯一
workbench-data数据块；schema 6 必须包含建档、系统、知识包、状态和来源核验信息。 -
接入完整计划：完整计划使用
plan_contract时，先运行Adapt-PlanContract.py适配为工作台主源；不得要求用户手工重写第二份计划 JSON。 -
链接打不开 / 跨电脑迁移异常：完整读取 路径可迁移修复协议，先盘点全部入口、配置和发布目标，再修复并执行整体移动回归；不得只修改截图中的单个按钮。
-
替换已有工作台壁纸：完整读取 壁纸替换，调用替换脚本完成备份、静态/动态模式、取景更新和检查；不得让用户手工改 HTML。
-
修改项目默认界面或默认背景：读取 视觉契约，修改源模板后用模板刷新脚本生成脱敏模板。
-
制作发布副本：读取 迁移与发布，先校验，再复制 HTML 和全部本地素材。
-
制定计划或训练复盘：转交对应训练 Skill；本 Skill 只消费结果，不凭空生成个人处方。
从零构建
- 确认目标目录、品牌短名、使用者称呼和周期开始日期。
- 优先使用用户自己的版本化计划 JSON。没有时可以用内置示例启动界面，但必须明确标注“示例数据”，不得把示例重量当成处方。
- 运行：
python "<skill>/scripts/Initialize-FitnessWorkbench.py" --target "<新项目目录>" --brand "TRAIN" --athlete "使用者" --start-date "YYYY-MM-DD" [--plan "<计划-vNN.json>"] [--notion "<notion-data.json>"]
- 初始化脚本必须创建正式 HTML、五个固定目录、背景素材、当前计划、执行基准和复盘索引，并自动运行构建与检查。
- 把页面中显示的示例计划替换为用户已确认的计划后，再交付为正式系统。
What ships with it
58 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 279 B
- assets/backgrounds/garou-cosmic-crouch.png 2740 KB
- assets/backgrounds/garou-landscape.png 2231 KB
- assets/backgrounds/garou-portrait.png 2635 KB
- assets/backgrounds/workbench-background.mp4 13731 KB
- assets/backgrounds/workbench-background.png 1665 KB
- assets/examples/cloudbase-release.example.json 490 B
- assets/examples/notion-data.example.json 807 B
- assets/examples/plan-template-v01.json 8.5 KB
- assets/ui-history.json 896 B
- assets/workbench-template.html 605 KB
- references/background-replacement.md 3.4 KB
- references/cloudbase-publishing.md 3.0 KB
- references/input-contract.md 8.1 KB
- references/migration-and-release.md 6.5 KB
- references/path-portability-repair.md 13 KB
- references/ui-upgrade.md 5.9 KB
- references/visual-contract.md 2.5 KB
- scripts/Adapt-PlanContract.py 5.5 KB runs code
- scripts/Build-FitnessWorkbenchData.py 93 KB runs code
- scripts/Check-FitnessWorkbench.py 34 KB runs code
- scripts/Check-FitnessWorkbenchBrowser.cjs 2.3 KB runs code
- scripts/Deploy-FitnessWorkbenchCloudBase.py 13 KB runs code
- scripts/Deploy-FitnessWorkbenchCloudBaseEncrypted.py 16 KB runs code
- scripts/Deploy-FitnessWorkbenchCloudBasePublicPersonal.py 10 KB runs code
- scripts/Initialize-FitnessWorkbench.py 14 KB runs code
- scripts/Inspect-FitnessWorkbench.py 7.4 KB runs code
- scripts/Migrate-FitnessWorkbenchSchema.py 2.0 KB runs code
- scripts/Prepare-FitnessWorkbenchEncryptedRelease.py 22 KB runs code
- scripts/Prepare-FitnessWorkbenchPublicPersonalRelease.py 11 KB runs code
- scripts/Prepare-FitnessWorkbenchRelease.py 23 KB runs code
- scripts/Publish-FitnessWorkbenchCloudBase.py 13 KB runs code
- scripts/Publish-FitnessWorkbenchCloudBasePrivate.py 14 KB runs code
- scripts/Publish-FitnessWorkbenchCloudBasePublicPersonal.py 9.9 KB runs code
- scripts/Refresh-FitnessWorkbench.py 34 KB runs code
- scripts/Refresh-FitnessWorkbenchTemplate.py 9.2 KB runs code
- scripts/Replace-FitnessWorkbenchBackground.py 9.7 KB runs code
- scripts/Test-FitnessWorkbenchBackgroundReplacement.py 8.3 KB runs code
- scripts/Test-FitnessWorkbenchCheckCliForwarding.py 2.7 KB runs code
- scripts/Test-FitnessWorkbenchCloudBasePrivatePublish.py 9.0 KB runs code
- scripts/Test-FitnessWorkbenchCloudBaseRelease.py 14 KB runs code
- scripts/Test-FitnessWorkbenchDataOnlyRefresh.py 5.0 KB runs code
- scripts/Test-FitnessWorkbenchEncryptedRelease.py 11 KB runs code
- scripts/Test-FitnessWorkbenchNotionSync.py 12 KB runs code
- scripts/Test-FitnessWorkbenchPortability.py 7.7 KB runs code
- scripts/Test-FitnessWorkbenchPublicPersonalRelease.py 15 KB runs code
- scripts/Test-FitnessWorkbenchRefresh.py 26 KB runs code
- scripts/Test-FitnessWorkbenchReleaseSafety.py 20 KB runs code
- scripts/Test-FitnessWorkbenchReviewProjection.py 2.5 KB runs code
- scripts/Test-FitnessWorkbenchUiUpgrade.py 11 KB runs code
- scripts/Test-FitnessWorkbenchWeekTransition.py 4.5 KB runs code
- scripts/Upgrade-FitnessWorkbenchUi.py 12 KB runs code
- scripts/Validate-FitnessWorkbenchSkill.py 13 KB runs code
- scripts/Verify-FitnessWorkbenchCloudBase.py 18 KB runs code
- scripts/Verify-FitnessWorkbenchCloudBaseEncrypted.py 5.7 KB runs code
- scripts/Verify-FitnessWorkbenchCloudBasePublicPersonal.py 3.8 KB runs code
- scripts/workbench_extras.py 563 B runs code
- scripts/workbench_ui.py 4.6 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.
- yesterday Changed · +7 lines df6eb1763151
- 7d ago Changed · +2 lines 49bd85a10c24
- 8d ago Changed · +38 lines d62b8caae4c9
- 13d ago First seen · 121 lines · 148 tokens per session scan A cdde8c2988cc
lzheng-fitness-workbench-builder is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (65 stars, last pushed 2d ago), licensed MIT. It adds 148 tokens to every session and 3,917 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…