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/child-safetygit 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 | $0.00011 | $0.04881 |
| Opus 5 | $0.00005 | $0.02440 |
| Sonnet 5 | $0.00002 | $0.00976 |
| Haiku 4.5 | $0.00001 | $0.00488 |
Grade A, and why
child-safety 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 — 755 lines — stays where its author put it; the contents beside it link to each section on GitHub.
儿童意外伤害预防与安全评估
儿童意外伤害预防和安全风险评估，覆盖家庭、交通、食品、水上等各类场景，提供年龄适配的安全建议。
操作类型
1. 记录安全评估 - record
记录儿童安全评估结果。
参数说明:
area: 安全区域（必填）- home: 家庭安全
- car: 交通/汽车安全
- water: 水上安全
- food: 食品安全
- outdoor: 户外/活动安全
date: 评估日期（可选，默认今天）
示例:
/child-safety record home
/child-safety record car 2025-01-14
执行步骤:
1. 读取儿童基础信息
从 data/profile.json 读取：
- 儿童姓名
- 出生日期
- 性别
如果缺少，提示：
⚠️ 未找到儿童档案
请先设置儿童基础信息：
/profile child-name 小明
/profile child-birth-date 2020-01-01
/profile child-gender male
2. 根据年龄确定检查项目
0-6个月（婴儿期）:
- 家庭：婴儿床安全、睡眠姿势、防窒息
- 抱姿：头部支撑
- 温度调节
6-12个月（爬行期）:
- 家庭：插座保护、防撞角、楼梯防护
- 小物品：防吞咽
- 烫伤防护
1-3岁（学步期）:
- 家庭：门窗锁、抽屉锁、阳台防护
- 厨房：刀具、化学品收纳
- 浴室：防滑、防溺水
3-6岁（学龄前）:
- 交通：安全座椅/增高垫
- 户外：走失预防
- 运动：护具使用
6-12岁（学龄期）:
- 交通：自行车安全、乘车安全
- 户外：陌生人危险
- 网络：网络安全教育
12-18岁（青春期）:
- 交通：驾驶安全（如适用）
- 运动：运动安全
- 社会：安全意识
3. 生成评估问题
根据年龄和区域，生成互动问题。
示例（1-3岁家庭安全）:
请回答以下安全问题（是/否）：
1. 所有插座是否已安装保护盖？
2. 家具尖锐角是否已安装防撞条？
3. 窗户是否安装了防护栏或限位器？
4. 清洁用品/药品是否放在儿童拿不到的地方？
5. 浴室是否铺设防滑垫？
4. 计算安全评分
safeCount = 用户回答"是"的数量
totalCount = 总问题数
safetyScore = (safeCount / totalCount) * 100
if safetyScore >= 90:
level = "excellent" // 优秀
else if safetyScore >= 70:
level = "good" // 良好
else if safetyScore >= 50:
level = "needs_attention" // 需要注意
else:
level = "high_risk" // 高风险
5. 生成评估报告
优秀示例:
✅ 家庭安全评估 - 优秀
评估信息：
━━━━━━━━━━━━━━━━━━━━━━━━━━
儿童：小明
年龄：2岁5个月
评估日期：2025年1月14日
评估区域：家庭安全
评估结果：
━━━━━━━━━━━━━━━━━━━━━━━━━━
安全等级：优秀 ✅
安全得分：90/100分
检查项目：
━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ 插座保护：已安装保护盖
✅ 防撞保护：家具尖角已处理
✅ 门窗防护：窗户已安装限位器
✅ 危险品收纳：药品/清洁品已收纳
✅ 浴室安全：已铺设防滑垫
建议：
━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ 继续保持良好的安全习惯
✅ 定期检查安全设施完好性
✅ 随着孩子成长调整安全措施
⚠️ 重要提示：
━━━━━━━━━━━━━━━━━━━━━━━━━━
本评估仅供参考，不能替代
专业安全检查。
如有特殊安全隐患，
请咨询相关专业人员。
数据已保存
需要注意示例:
⚠️ 家庭安全评估 - 需要注意
评估信息：
━━━━━━━━━━━━━━━━━━━━━━━━━━
儿童：小明
年龄：2岁5个月
评估日期：2025年1月14日
评估区域：家庭安全
评估结果：
━━━━━━━━━━━━━━━━━━━━━━━━━━
安全等级：需要注意 ⚠️
安全得分：60/100分
检查项目：
━━━━━━━━━━━━━━━━━━━━━━━━━━
✅ 插座保护：已安装保护盖
✅ 防撞保护：家具尖角已处理
⚠️ 门窗防护：窗户缺少防护措施
❌ 危险品收纳：药品放在易取得处
✅ 浴室安全：已铺设防滑垫
需要改进：
━━━━━━━━━━━━━━━━━━━━━━━━━━
🔴 紧急：窗户安装防护栏/限位器
🔴 紧急：药品移至儿童拿不到的高处/带锁柜
建议措施：
━━━━━━━━━━━━━━━━━━━━━━━━━━
1. 立即安装窗户防护装置
2. 购买药品安全收纳盒
3. 检查所有窗户的安全性
4. 教育孩子不攀爬窗户
🏚️ 家庭安全小贴士：
━━━━━━━━━━━━━━━━━━━━━━━━━━
• 窗户旁不要放置可攀爬家具
• 阳台门应随时关闭
• 药品应存放在带锁容器中
• 清洁剂应存放在原容器中
⚠️ 重要提示：
━━━━━━━━━━━━━━━━━━━━━━━━━━
高处坠落是儿童意外伤害的
主要原因之一，请务必重视！
数据已保存
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 · 755 lines · 11 tokens per session scan A 882087879a99
child-safety is a command published in the GitHub repository huifer/WellAlly-health (935 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 4,881 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.