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/growthgit 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 | $0.00012 | $0.05270 |
| Opus 5 | $0.00006 | $0.02635 |
| Sonnet 5 | $0.00002 | $0.01054 |
| Haiku 4.5 | $0.00001 | $0.00527 |
Grade A, and why
growth 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 — 786 lines — stays where its author put it; the contents beside it link to each section on GitHub.
生长曲线追踪
儿童生长监测和评估，基于WHO儿童生长标准，提供百分位分析和生长异常预警。
操作类型
1. 记录生长数据 - record
记录儿童身高、体重、头围等生长指标。
参数说明:
info: 测量信息（必填）- 身高：height 112.5, 112.5cm
- 体重：weight 20.5, 20.5kg
- 头围：head 48, 48cm（0-3岁）
date: 测量日期（可选，默认今天）
示例:
/growth record 112.5cm 20.5kg
/growth record height 112.5 weight 20.5
/growth record head 48
/growth record height 110 weight 18.5 date 2025-06-15
执行步骤:
1. 解析测量信息
参数识别:
- 身高：
height[:\s]+(\d+\.?\d*)或(\d+\.?\d*)\s*cm - 体重：
weight[:\s]+(\d+\.?\d*)或(\d+\.?\d*)\s*kg - 头围：
head[:\s]+(\d+\.?\d*)或(\d+\.?\d*)\s*cm
2. 读取儿童基础信息
从 data/profile.json 读取：
- 出生日期
- 性别
如果缺少，提示：
⚠️ 缺少儿童基础信息
请先设置：
/profile child-name 小明
/profile child-birth-date 2020-01-01
/profile child-gender male
3. 计算年龄和月龄
birthDate = profile.child_birth_date
measurementDate = date || today
ageMonths = (measurementDate - birthDate) / 30.44
ageYears = ageMonths / 12
// 早产儿矫正（如需要）
if gestational_age < 37 weeks and age < 2 years:
correctedAge = chronologicalAge - (40 - gestational_age)
4. 计算BMI
if height && weight:
bmi = weight / (height / 100)²
5. 查找WHO百分位
从 data/who-growth-standards.json 查找：
height_for_age→ 年龄别身高百分位weight_for_age→ 年龄别体重百分位bmi_for_age→ 年龄别BMI百分位head_circumference_for_age→ 年龄别头围百分位（0-3岁）
百分位查找算法:
// 1. 选择性别和测量类型
whoData = loadWHOStandards()[measurementType][gender]
// 2. 查找年龄对应的百分位
ageKey = findNearestAge(whoData, ageMonths)
percentiles = whoData[ageKey]
// 3. 计算百分位和Z-score
percentile = calculatePercentile(value, percentiles)
zScore = calculateZScore(value, percentiles)
6. 计算Z-score（标准差单位）
zScore = (value - median) / standardDeviation
// Z-score分级：
// < -3: 严重偏低
// -3 to -2: 明显偏低
// -2 to -1: 轻度偏低
// -1 to +1: 正常
// +1 to +2: 轻度偏高
// +2 to +3: 明显偏高
// > +3: 严重偏高
7. 计算生长速度（如果有历史数据）
if measurements.length >= 2:
previous = measurements[measurements.length - 2]
current = measurements[measurements.length - 1]
monthsDiff = calculateMonthsDifference(previous.date, current.date)
heightVelocity = (current.height - previous.height) / (monthsDiff / 12)
weightVelocity = (current.weight - previous.weight) / (monthsDiff / 12)
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 · 786 lines · 12 tokens per session scan A c5554470c746
growth is a command published in the GitHub repository huifer/WellAlly-health (935 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 5,270 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.