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-nutrition-systemgit 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-nutrition-system)<a href="https://agentmods.dev/skills/lzheng0411/lzheng-fitness/lzheng-nutrition-system"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-nutrition-system/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-nutrition-system"><img src="https://agentmods.dev/badge/skills/lzheng0411/lzheng-fitness/lzheng-nutrition-system.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 | $0.00080 | $0.00960 |
| Opus 5 | $0.00040 | $0.00480 |
| Sonnet 5 | $0.00016 | $0.00192 |
| Haiku 4.5 | $0.00008 | $0.00096 |
Grade A, and why
lzheng-nutrition-system 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.
What it actually says
Lzheng 通用营养系统
本 Skill 只负责营养建档、nutrition_contract、日型目标和复盘候选。训练计划决定日型，不按单次训练手表消耗临时补吃；工作台负责展示和记录，不能反向发明处方。
开始前
- 完整读取 营养协议。
- 读取当前训练计划的真实日期排程、最近体重/腰围趋势、执行率、训练表现和已确认餐食；缺失或过期时标为待校准。
- 营养变量按需读取
../lzheng-training-expert-library的 Alan Aragon 模块。 - 先确认目标、年龄、身高、当前体重、饮食环境、预算、医生已确认限制和主要执行障碍；未收敛前不输出精确热量。
用户流程
建档 → 得到当天目标 → 拍照或文字记录 → 查看区间估算 → 饭后反馈 → 用户确认入账 → 查看剩余 → 两周复盘
- 照片输出只能是候选区间、置信度和误差来源。
estimate是上桌总量，consumed_estimate是实际摄入候选，confirmed_nutrition才是正式入账。- 只有用户主动创建任务并显式运行一次 Agent 才允许识别；空队列不调用模型，网页不自动轮询。
- 用户可以在候选区间内做确定性微调并保留
agent_best/user_adjusted/user_manual来源。 - 已确认记录的更正必须留痕；不能静默覆盖原值。
固定边界
- 热量公式只是起点，至少用两周同条件体重趋势、腰围、训练表现和执行率校准。
- 当前体重未知时保留
awaiting_profile，不生成伪精确目标。 - 蛋白质和脂肪保持相对稳定，训练日型主要调整碳水；七日加权平均必须符合周目标。
- 食堂、外卖和照片估算始终保留范围；压力进食后不使用禁食或惩罚性有氧补偿。
- 医疗、肾脏疾病、糖尿病、进食障碍、孕期、过敏或药物相关需求转交合格专业人员；急性严重症状立即就医。
- 个人照片、账号、密钥、环境 ID、Notion 地址和真实餐食数据不得进入公开模板或示例。
生成与交接
验证结构化协议：
python scripts/validate_nutrition_contract.py <nutrition-contract-vNN.json>
协议通过且用户确认后，保存为当前系统的营养主源，并创建 nutrition_contract_updated 交接给 lzheng-fitness-workbench-builder。交接只传相对路径和确认状态；工作台刷新、发布副本、部署和线上验证必须分别报告。
完成闸门
- validator 与
test_nutrition_system.py通过； - 当天日型来自真实日期排程，未知日期不猜测；
- 周平均、宏量换算和调整上限通过测试；
- 估算、实际摄入候选与确认入账三段没有混用；
- 默认无自动触发器、无后台空查、无自动确认；
- 示例保持匿名且体重为
null，不得出现虚构处方或私人配置。
视频学习与三餐报餐
用户要把学到的饮食方法用于三餐、文字/照片报餐或标签复用时，读取 学习与报餐。保留用户接受的方法和目标版本，不用新的菜单替换计算依据。
What ships with it
7 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 322 B
- assets/examples/nutrition-contract.example.json 1.3 KB
- references/learning-and-meals.md 2.3 KB
- references/nutrition-contract.md 2.4 KB
- scripts/test_nutrition_system.py 1.4 KB runs code
- scripts/update_planner.py 2.9 KB runs code
- scripts/validate_nutrition_contract.py 3.5 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 · +4 lines e593611520ee
- 8d ago First seen · 54 lines · 80 tokens per session scan A e875ba25dc83
lzheng-nutrition-system is a skill published in the GitHub repository LZheng0411/Lzheng-fitness (65 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 960 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.