WellAlly-health: Command for Claude Code

.claude/commands/save-report.md

save-report is a command for Claude Code from huifer/WellAlly-health. It costs 9 tokens per session (5,110 once invoked), scanned A, original, MIT.

A command for saving a medical examination report from an image into a personal health data centre.

In plain words
What is it for?
Use it with a report image to extract the date, institution, test results, units, reference ranges, and abnormal markers, then save the report.
Why use it?
It reduces manual entry by reading the report and choosing an examination date from the supplied date or the dates shown in the image.

Command for Claude Code

Written for Claude Code: arguments in frontmatter.

This is huifer/WellAlly-health's own configuration. It tells Claude Code how to work on WellAlly-health itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything WellAlly-health configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/huifer/WellAlly-health/main/.claude/commands/save-report.md
Clone the repo
git clone --depth 1 https://github.com/huifer/WellAlly-health

Made for: Claude Code.

Wrote 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.

agentmods badge for save-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/huifer/wellally-health/save-report/github.svg)](https://agentmods.dev/commands/huifer/wellally-health/save-report)
Your own site
<a href="https://agentmods.dev/commands/huifer/wellally-health/save-report"><img src="https://agentmods.dev/badge/commands/huifer/wellally-health/save-report/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.

agentmods 80×15 button for save-report

Your own site · 80×15
<a href="https://agentmods.dev/commands/huifer/wellally-health/save-report"><img src="https://agentmods.dev/badge/commands/huifer/wellally-health/save-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,110 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.05110
Opus 5 $0.00005 $0.02555
Sonnet 5 $0.00002 $0.01022
Haiku 4.5 $0.00001 $0.00511

Measured 10d ago against content hash a13bcbe1c4a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

save-report 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.

.claude/commands/save-report.md · 408 lines

How it starts

The opening of the file, as written. The whole thing — 408 lines — stays where its author put it; the contents beside it link to each section on GitHub.

保存医疗检查单

你需要保存用户提供的医疗检查单到个人医疗数据中心。

参数说明:

  • image_path(必填):检查单图片的本地路径
  • exam_date(可选):检查日期,格式为 YYYY-MM-DD。如果提供此参数,将直接使用该日期;如果未提供,将从图片中自动提取日期。

任务步骤

  1. 检查参数

    • 检查用户是否提供了 exam_date 参数
    • 如果提供了 exam_date
      • 验证日期格式是否为 YYYY-MM-DD
      • 直接使用该日期作为检查日期
      • 在分析图片时仍然提取日期信息用于验证,但不覆盖用户提供的日期
    • 如果未提供 exam_date
      • 从图片中自动提取日期(遵循下方"日期提取规则")
  2. 读取并分析图片

    • 使用 Read 工具读取用户提供的检查单图片
    • 使用 mcp__4_5v_mcp__analyze_image 工具分析图片内容,重点提取日期信息

    图片分析提示词模板(生化检查):

    请详细识别这张医疗检验报告单中的所有信息,包括:
    
    1. **日期时间信息(最重要):**
       - 采样时间/标本采集时间
       - 送检时间/送样时间
       - 检测时间/报告时间
       - 其他日期标识
    
    2. 医院/检验机构名称
    
    3. 检验项目和结果:
       - 检验项目名称
       - 检验数值
       - 单位
       - 参考范围(最小值和最大值)
       - 异常标识(箭头↑↓或其他)
    
    请按结构化格式列出所有信息,日期时间请特别标注并说明是哪种类型的时间。
    

    图片分析提示词模板(影像检查): 根据检查类型使用对应的提示词模板(见下方"影像检查详细分析模板")

    • 识别检查单类型:生化检查 vs 影像检查
  3. 提取数据 分析图片内容并提取以下信息:

    日期确定规则(重要):

    • 优先级1(最高): 用户通过 exam_date 参数提供的日期
    • 优先级2: 图片中的采样时间(如"采样时间"、"标本采集时间")
    • 优先级3: 图片中的送样时间(如"送检时间"、"送样时间")
    • 优先级4: 图片中的检测时间/报告时间(如"检测时间"、"报告时间")
    • 优先级5: 图片中的其他日期标识(如"检查日期"、"检验日期")
    • 优先级6(最低): 仅当以上所有时间都无法提取时,才使用当前日期作为备选

    日期格式处理:

    • 识别并转换各种日期格式:YYYY-MM-DD、YYYY/MM/DD、YYYY年MM月DD日、MM-DD-YYYY等
    • 统一转换为 YYYY-MM-DD 格式存储

    如果是生化检查(验血、验尿等):

    • 检查日期(按上述优先级确定)
    • 各项检查指标:
      • 检查项目名称
      • 检查数值
      • 单位
      • 参考区间(最小值、最大值)
      • 是否异常(带箭头标识的)

    如果是影像检查(B超、CT、MRI、X光等):

    • 检查日期(按上述优先级确定)
    • 检查类型(B超/CT/MRI/X光/内窥镜/病理/心电图/乳腺钼靶/PET-CT等)
    • 检查部位
    • 检查所见/描述(详细的影像学描述)
    • 测量数据(尺寸、数值等具体测量参数)
    • 检查结论/诊断意见
    • 特异性指标(根据不同检查类型提取,见下方影像检查详细分析模板)
  4. 生成数据文件 根据检查类型生成 JSON 文件:

    文件路径格式:

    • 生化检查:data/生化检查/YYYY-MM/YYYY-MM-DD_检查类型.json
    • 影像检查:data/影像检查/YYYY-MM/YYYY-MM-DD_检查类型_检查部位.json

    JSON 数据结构:

    生化检查:

    {
      "id": "{{生成唯一ID,使用日期+时间戳}}",
      "type": "生化检查",
      "date": "YYYY-MM-DD",
      "hospital": "医院名称(如能识别)",
      "original_image": "images/{{原始图片文件名}}",
      "items": [
        {
          "name": "检查项目名称",
          "value": "检查值",
          "unit": "单位",
          "min_ref": "参考区间最小值",
          "max_ref": "参考区间最大值",
          "is_abnormal": true/false
        }
      ]
    }
    

Read the full file on GitHub · 408 lines

Changes

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.

  1. 10d ago First seen · 408 lines · 9 tokens per session scan A a13bcbe1c4a5

Subscribe to this mod's changes

save-report 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 5,110 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.