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 agentmods add commands/huifer/wellally-health/diabetesgit clone --depth 1 https://github.com/huifer/WellAlly-healthWhat 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 | $0.00021 | $0.04279 |
| Opus 5 | $0.00010 | $0.02139 |
| Sonnet 5 | $0.00004 | $0.00856 |
| Haiku 4.5 | $0.00002 | $0.00428 |
Grade A, and why
diabetes 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 — 526 lines — stays where its author put it; the contents beside it link to each section on GitHub.
糖尿病管理
全面的血糖监测和糖尿病管理，帮助控制血糖、预防并发症。
⚠️ 医学安全声明
重要提示：本系统仅供健康监测记录，不能替代专业医疗诊断和治疗。
- ❌ 不给出具体用药剂量调整建议
- ❌ 不直接开具处方药或推荐具体药物
- ❌ 不替代医生诊断和治疗决策
- ❌ 不判断疾病预后或并发症发生
- ✅ 提供血糖监测记录和趋势分析（仅供参考）
- ✅ 提供HbA1c追踪和达标情况
- ✅ 提供并发症筛查记录和提醒
- ✅ 提供低血糖事件记录和分析
- ✅ 提供生活方式建议和就医提醒
所有用药方案和治疗决策请遵从医生指导。
操作类型
1. 记录血糖 - record
记录血糖测量数据。
参数说明：
info: 血糖信息（必填），使用自然语言描述
示例：
/glucose record fasting 6.5
/glucose record postprandial 8.2
/glucose record bedtime 7.2
/glucose record random 9.5
/glucose record fasting 6.8 before breakfast
支持的血糖类型：
- fasting：空腹血糖（目标：4.4-7.0 mmol/L）
- postprandial / postprandial_2h：餐后2小时血糖（目标：<10.0 mmol/L）
- bedtime：睡前血糖（目标：6.0-9.0 mmol/L）
- random：随机血糖
执行步骤：
- 解析血糖数值和测量类型
- 生成记录ID和时间戳
- 保存到
data/diabetes-tracker.json - 更新血糖统计
- 输出确认信息
2. 记录HbA1c - hba1c
记录糖化血红蛋白检测结果。
示例：
/glucose hba1c 6.8
/glucose hba1c 7.2 2025-06-15
/glucose hba1c history
执行步骤：
- 解析HbA1c数值
- 计算与上次检测结果的变化
- 保存到历史记录
- 判断是否达标（目标：<7.0%）
- 输出趋势分析
3. 查看血糖趋势 - trend
查看血糖变化趋势。
示例：
/glucose trend
/glucose trend 7days
/glucose trend this month
输出内容：
- 血糖趋势图（文字描述）
- 日内血糖波动
- 低血糖/高血糖事件
- 达标情况
4. 查看TIR - tir
查看葡萄糖目标范围内时间（Time in Range）。
示例：
/glucose tir
/glucose tir 14days
输出内容：
- TIR百分比（目标：>70%）
- 目标范围内时间（小时）
- 高于范围时间（小时）
- 低于范围时间（小时）
- 测量周期
TIR定义（一般糖尿病患者）：
- 目标范围：3.9-10.0 mmol/L
- TIR目标：>70%
- 高于范围：<10%
- 低于范围：<4%
5. 记录低血糖事件 - hypo
记录低血糖事件详情。
示例：
/glucose hypo 3.4 sweating
/glucose hypo 2.8 confusion took glucose
/glucose hypo 3.0 palpitations tremor juice
/glucose hypo history
低血糖分级：
- 1级：血糖 <3.9 mmol/L，但≥3.0 mmol/L
- 2级：血糖 <3.0 mmol/L
- 3级：严重低血糖，需要他人帮助
支持的症状记录：
- sweating（出汗）
- palpitations（心悸）
- tremor（颤抖）
- hunger（饥饿）
- confusion（意识模糊）
- dizziness（头晕）
处理建议：
⚠️ 检测到低血糖（<3.9 mmol/L）
立即处理：
━━━━━━━━━━━━━━━━━━━━━━━━━━
1. 服用15g快速升糖食物
• 3-5颗葡萄糖片
• 150ml果汁或含糖饮料
• 1汤匙蜂蜜
2. 等待15分钟后复测
3. 如仍低于3.9 mmol/L，重复步骤1
4. 血糖恢复正常后，如距下一餐>1小时，
进食少量长效碳水化合物
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 First seen · 526 lines · 21 tokens per session scan A 5c084bc6447b
diabetes is a command published in the GitHub repository huifer/WellAlly-health (935 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 4,279 once invoked, about $0.0001 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.