Borrowing it
Nothing to install: this file belongs to huifer/WellAlly-health. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/huifer/WellAlly-health/main/.claude/commands/medication.mdgit clone --depth 1 https://github.com/huifer/WellAlly-healthWrote 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/commands/huifer/wellally-health/medication)<a href="https://agentmods.dev/commands/huifer/wellally-health/medication"><img src="https://agentmods.dev/badge/commands/huifer/wellally-health/medication/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/commands/huifer/wellally-health/medication"><img src="https://agentmods.dev/badge/commands/huifer/wellally-health/medication.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 | $0.00009 | $0.12150 |
| Opus 5 | $0.00005 | $0.06075 |
| Sonnet 5 | $0.00002 | $0.02430 |
| Haiku 4.5 | $0.00001 | $0.01215 |
Grade A, and why
medication 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 10d 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 — 1,533 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用药记录管理
管理药物和用药计划,记录每日用药情况,追踪药物依从性。
操作类型
1. 添加药物 - add
添加新药物及其用药计划。
参数说明:
info: 药物信息(必填),使用自然语言描述
示例:
/medication add 阿司匹林 100mg 每天1次 早餐后服用
/medication add 氨氯地平 5mg 每天早晚各1次
/medication add 二甲双胍 500mg 每天3次 餐后服用
/medication add 维生素D 1000IU 每周1次
支持的描述格式:
- 药物名称 + 剂量 + 频率 + 用药时间
- 频率关键词:每天、每日、每周、隔天、按需
- 时间关键词:早餐前、早餐后、午餐前、午餐后、晚餐前、晚餐后、睡前、早晚各一次等
2. 记录用药 - log
记录实际用药情况。
参数说明:
info: 用药记录(必填),使用自然语言描述
示例:
/medication log 已服用 阿司匹林
/medication log 阿司匹林 已服
/medication log 忘记服用 氨氯地平
/medication log 氨氯地平 漏服
/medication log 阿司匹林 早上8点已服
自动识别:
- ✅ 已服用、已服、服了、吃了 - 正常用药
- ❌ 忘记、漏服、未服 - 漏服记录
- ⏰ 计划 - 预定提醒
3. 查看药物列表 - list
查看所有已添加的药物及用药计划。
示例:
/medication list
4. 查看用药历史 - history
查看用药记录历史。
示例:
/medication history
/medication history today
/medication history 2025-12-31
/medication history week
5. 查看用药统计 - status
查看用药依从性统计。
示例:
/medication status
/medication status today
/medication status week
/medication status month
执行步骤
添加药物 (add)
1. 解析药物信息
从自然语言中提取:
- 药物名称:通用名或商品名
- 剂量:数值 + 单位(mg、g、ml、IU、片、粒等)
- 频率:每天次数、每周次数等
- 用药时间:具体的服药时间点
- 特殊说明:餐前、餐后、睡前等
2. 生成用药计划
核心规则:schedule 数组必须为每周的每一天(1-7)明确生成用药计划记录
频率映射规则:
| 用户输入 | 频率类型 | schedule 记录数 | 生成规则 |
|---|---|---|---|
| 每天1次、每日1次 | daily | 7条 | 每天1条,周一至周日 |
| 每天2次、每日2次、早晚各一次 | daily | 14条 | 每天2条,周一至周日 |
| 每天3次、每日3次、一日三次 | daily | 21条 | 每天3条,周一至周日 |
| 每周1次 | weekly | 1条 | 仅指定星期几 |
| 隔天1次 | every_other_day | 4条 | 周一、三、五、日 或 二、四、六 |
| 按需 | as_needed | 0条 | 无固定计划 |
schedule 生成算法:
// 伪代码示例
function generateSchedule(frequency, times, timeSlots) {
const schedule = [];
if (frequency === 'daily') {
// 每天 N 次:为每周7天每天生成 N 条记录
for (let weekday = 1; weekday <= 7; weekday++) {
for (const timeSlot of timeSlots) {
schedule.push({
weekday: weekday,
time: timeSlot.time,
timing_label: timeSlot.label,
dose: {
value: timeSlot.dose.value,
unit: timeSlot.dose.unit
}
});
}
}
} else if (frequency === 'weekly') {
// 每周一次:仅生成1条记录(默认周一,可通过用户输入指定)
schedule.push({
weekday: 1, // 或用户指定的星期几
time: timeSlots[0].time,
timing_label: timeSlots[0].label,
dose: {
value: timeSlots[0].dose.value,
unit: timeSlots[0].dose.unit
}
});
} else if (frequency === 'every_other_day') {
// 隔天一次:生成4条记录(1,3,5,7 或 2,4,6)
const days = [1, 3, 5, 7]; // 或 [2, 4, 6]
for (const weekday of days) {
schedule.push({
weekday: weekday,
time: timeSlots[0].time,
timing_label: timeSlots[0].label,
dose: {
value: timeSlots[0].dose.value,
unit: timeSlots[0].dose.unit
}
});
}
}
return schedule;
}
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.
- 10d ago First seen · 1,533 lines · 9 tokens per session scan A af505a21bf4e
medication is a command published in the GitHub repository huifer/WellAlly-health (943 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 12,150 once invoked, about $0.0000 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 commands, from other repositories
health
Run health checks on the Claude orchestration system.
health
Scan all projects for stale research, forgotten ADRs, unresolved review conditions, orphaned artifacts, missing traceability, and version drift.
roster-doctor
Health check and dev-environment pre-flight for the roster install and its build/test/lint tooling.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.