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-plangit 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-plan)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-fitness-plan"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-fitness-plan/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-plan"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-fitness-plan.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 | $0.00144 | $0.03391 |
| Opus 5 | $0.00072 | $0.01695 |
| Sonnet 5 | $0.00029 | $0.00678 |
| Haiku 4.5 | $0.00014 | $0.00339 |
Grade A, and why
lzheng-fitness-plan 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lzheng 个性化健身计划
把计划视为基于某一时间点用户状态的可验证训练假设。先建档、再分层、再选动作和训练变量，最后从同一份结构化数据生成文字与 HTML。
读取模式
从零建档、结构性重做，或目标、频率、训练条件、安全限制、动作选择、训练量发生变化时，依次读取：
- 知识路由：确定本次应读取的内置知识与联网来源。
- 问诊与状态快照：收集必要信息并生成不可覆盖的时间快照。
- 训练者分层：判断整体 P0—L3 和单动作等级。
- 动作适配：选择固定器械、自由重量、自重或绳索动作。
- 计划设计：确定目标、频率、分化、训练量、渐进和短期降级。
- 计划数据协议：建立唯一
plan_contract。 - 计划页面视觉契约：固定页面结构、导航、模板资产和设计边界。
- HTML 输出规范：生成和审计最终页面。
- 证据基础：核验安全、训练频率、器械选择和公共活动量的来源边界。
- 训练专家选择协议：仅在专家变量会改变计划时选择最少必要来源模块。
不要凭模型记忆代替 Skill 内置资料。只读取知识路由为当前问题指定的参考文件；涉及容易变化的安全或公共指南时再联网核验官方来源。
低 token 局部修订
如果只修改已确认的日期排程、计划版本、训练周次、工作重量、次数/RPE 或由正式复盘明确给出的下一次处方，并且目标、频率、器械、健康限制、动作结构和周训练量均不变，则使用局部修订模式：
- 先运行
lzheng-training-system inspect --root "<系统根目录或训练项目根目录>"，不得读取整份健身工作台.html。 - 只读取摘要中
authoritative_sources指向的当前计划 JSON、当前执行基准和本次复盘/交接；不扫描历史计划、全部复盘、完整专家库或工作台模板。 - 必读
references/plan-contract.md；只有被修改变量涉及对应规则时，才读取动作、计划设计或证据参考。 - 在同一份当前计划结构上产生新版本 JSON，并重新运行完整 JSON 校验、HTML 渲染和 HTML 审计；校验完整不等于重新读取全部资料。
- 独立计划 HTML 只能写入计划目录，绝不得覆盖
健身工作台.html。创建LZHENG_HANDOFF后由process-handoffs刷新工作台数据块。
无法确认是否属于局部修订时，按结构性重做处理。出现疼痛、疾病、停训或训练条件变化时不得使用低 token 模式绕过安全分流。
专家知识路由
专家库是内部来源层，不是另一个处方系统。目标含营养、肌肥大、计划结构、专项力量、反复中断或已获专业允许活动后的返场变量时，先按专家选择协议读取 ../lzheng-training-expert-library/references/expert-registry.json，再进入对应模块。默认 1 位；只有独立变量或真实冲突才增加。专家只提供来源限定判断，计划事实、最终处方、版本和写入仍由本 Skill 所有。实际采用时按专家库输出协议展示；未采用时不增加专家区块。
执行流程
1. 确认任务边界
- 用户只问原则或解释时，回答问题，不自动创建状态档案或计划文件。
- 用户要求制定、重做或调整完整计划时，执行完整流程。
- 用户明确要求单个力量动作的 8—12 周周期，或明确确认专项周期建议时，才调用
lzheng-strength-cycle-planner。 - 不因用户只提到“力量提升”自动调用周期 Skill；没有确认时使用普通渐进。
- 用户停训达到 7 天、连续漏练 3 次、疾病后恢复、训练条件明显改变或 4 周内反复中断时，路由到
lzheng-training-return。 - 漏练 1—2 次、单日状态差或时间不足仍由本 Skill 处理。
What ships with it
16 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 363 B
- assets/fitness-plan-template.html 13 KB
- assets/header-lineart.png 1441 KB
- references/evidence-base.md 2.1 KB
- references/exercise-selection.md 3.3 KB
- references/fitness-ui-contract.md 2.2 KB
- references/html-output-spec.md 2.9 KB
- references/intake-and-state-snapshot.md 2.9 KB
- references/knowledge-routing.md 2.4 KB
- references/plan-contract.example.json 11 KB
- references/plan-contract.md 8.8 KB
- references/program-design.md 3.2 KB
- references/trainee-classification.md 2.6 KB
- scripts/audit_html_plan.py 4.3 KB runs code
- scripts/render_fitness_plan.py 18 KB runs code
- scripts/validate_plan.py 21 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.
- 8d ago Changed · +12 lines 0c36ac285922
- 12d ago First seen · 144 lines · 144 tokens per session scan A de1521b755e8
lzheng-fitness-plan is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (65 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 3,391 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…