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 JuneYaooo/mediwise-health-suite --skill diet-trackergit clone --depth 1 https://github.com/JuneYaooo/mediwise-health-suiteWrote 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/juneyaooo/mediwise-health-suite/diet-tracker)<a href="https://agentmods.dev/skills/juneyaooo/mediwise-health-suite/diet-tracker"><img src="https://agentmods.dev/badge/skills/juneyaooo/mediwise-health-suite/diet-tracker/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/juneyaooo/mediwise-health-suite/diet-tracker"><img src="https://agentmods.dev/badge/skills/juneyaooo/mediwise-health-suite/diet-tracker.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 | $0.00039 | $0.03389 |
| Opus 5.5 | $0.00016 | $0.01356 |
| Sonnet 5.5 | $0.00008 | $0.00678 |
| Haiku 4.5 | $0.00004 | $0.00339 |
Grade A, and why
diet-tracker 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 2mo 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MediWise · 饮食追踪 Skill
概述
提供每餐饮食记录、食物条目管理、每日/每周营养摘要、热量趋势分析等功能。与 mediwise-health-tracker 共享数据库，可与 weight-manager 联动形成"饮食 → 热量 → 体重"完整闭环。
本 Skill 只记录和展示饮食数据、数据来源、用户目标差异与记录完整度，不提供营养治疗或饮食指导。内置参考区间只用于客观对比，不据此推荐用户增加、减少或替换食物。
数据模型
diet_records（一餐记录）
| 字段 | 说明 |
|---|---|
| id | 记录 ID |
| member_id | 成员 ID |
| meal_type | 餐次: breakfast/lunch/dinner/snack |
| meal_date | 日期 YYYY-MM-DD |
| meal_time | 时间 HH:MM（可选） |
| total_calories | 总热量 kcal（见下方三态说明） |
| total_protein | 总蛋白质 g（见下方三态说明） |
| total_fat | 总脂肪 g（见下方三态说明） |
| total_carbs | 总碳水 g（见下方三态说明） |
| total_fiber | 总膳食纤维 g（见下方三态说明） |
| note | 备注 |
diet_items（食物条目）
| 字段 | 说明 |
|---|---|
| id | 条目 ID |
| record_id | 关联 diet_records.id |
| food_name | 食物名称 |
| amount | 数量 |
| unit | 单位（g/ml/份/个等） |
| calories | 热量 kcal（见下方三态说明） |
| protein | 蛋白质 g（见下方三态说明） |
| fat | 脂肪 g（见下方三态说明） |
| carbs | 碳水 g（见下方三态说明） |
| fiber | 膳食纤维 g（见下方三态说明） |
| note | 备注 |
营养字段的三态语义（饮食数据完整性的基础，读取方必须按此解释）：
| 存储值 | 含义 | 产生方式 |
|---|---|---|
NULL |
未知——没查过、查询失败、或数据源里没有 | 未提供营养值时尝试补全，补全失败即写 NULL，并在 note 标注 [未解析营养] |
0 |
确为零——用户或数据源明确给出 0 | 只在显式传入 0 时写入（水、黑咖啡、无糖茶等） |
> 0 |
已确认的数值 | 由数据源或用户标签提供 |
NULL 与 0 不可互换：把未知当成 0 会在下游凭空造出「热量收支」。因此按日汇总时，只要当天任一餐的某字段为 NULL，该字段当天的总计就是未知（混合餐次会同时给出已知部分的合计，但不得对外报成完整值），未解析的日期不进入任何平均值分母，只作为「未解析天数」单独报告。逐字段判断，不要只看热量——否则一个未解析的 fat 会被当成 0 系统性拉低三大营养素比例。
功能列表
diet.py — 饮食记录 CRUD
| 动作 | 子命令 | 必要参数 | 可选参数 | 说明 |
|---|---|---|---|---|
| add-meal | add-meal | --member-id, --meal-type, --meal-date | --meal-time, --note, --items (JSON) | 添加一餐记录（可同时包含多个食物条目），返回 nutrition_status 等字段，见下方响应契约 |
| add-item | add-item | --record-id, --food-name | --amount, --unit, --calories, --protein, --fat, --carbs, --fiber, --note | 向已有餐次追加食物条目；也可用于事后补全未解析的营养值（补全后餐次自动重新汇总） |
| list | list | --member-id | --date, --start-date, --end-date, --meal-type, --limit | 查看饮食记录 |
| delete | delete | --id | --type (record/item) | 删除记录或条目 |
| daily-summary | daily-summary | --member-id, --date | 某日营养摘要 |
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.
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.
- 2mo ago Changed · +31 lines d072aff5ce68
- 2mo ago First seen · 132 lines · 39 tokens per session scan A 132cecb62fbe
diet-tracker is a skill published in the GitHub repository JuneYaooo/mediwise-health-suite (37 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 3,389 once invoked, about $0.0002 per session on Opus 5.5. 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.
diet-tracker compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diet-trackerJuneYaooo/mediwise-health-suite | Skill | 37 | 1mo ago | MIT | A | 39 | Codex |
| tmuxHKUDS/nanobot | Skill | 50k | today | MIT | A | 20 | Claude Code, Codex |
| add-matrixnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 19 | Claude Code |
| add-resendnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 16 | Claude Code |
| add-macos-statusbarnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 49 | Claude Code |
| sandbaseiflytek/skillhub | Skill | 5.4k | yesterday | Apache-2.0 | A | 67 | Claude Code |
| agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 115 | Claude Code, Codex |