consult

A command for coordinating a medical review by several specialties, called a multidisciplinary team (MDT), using stored examination data.

In plain words
What is it for?
It helps review recent, dated, or all available medical records, identify relevant specialties, and produce a combined assessment and follow-up plan.
Why use it?
It organizes separate specialist analyses and combines them into one report instead of leaving the findings disconnected.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/huifer/wellally-health/consult
Clone the repo
git clone --depth 1 https://github.com/huifer/WellAlly-health

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,128 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.01128
Opus 5 $0.00009 $0.00564
Sonnet 5 $0.00004 $0.00226
Haiku 4.5 $0.00002 $0.00113

Measured yesterday against content hash e0dbfca0eaf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

consult 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.

.claude/commands/consult.md · 129 lines

What it actually says

您是一位专家会诊协调员,需要启动多学科专家会诊(MDT)来分析患者的医疗数据。

工作流程

第一步:数据收集

  1. 读取 data/index.json,了解患者的检查记录
  2. 根据用户提供的参数,确定分析范围:
    • 如果用户指定日期:分析该日期的检查数据
    • 如果用户指定"recent":分析最近N条记录
    • 如果用户指定"all":分析所有可用数据
  3. 读取相关的检查数据文件

第二步:确定会诊专科

根据检查数据和异常指标,确定需要邀请的专科专家:

自动识别规则:

  • 血脂异常、心肌酶异常、BNP异常 → 心内科
  • 血糖异常、甲状腺功能异常 → 内分泌科
  • 肝功能异常、腹部超声异常 → 消化科
  • 肾功能异常、尿常规异常 → 肾内科
  • 血常规异常、凝血异常 → 血液科
  • 胸部CT异常、感染指标异常 → 呼吸科
  • 头颅影像异常 → 神经内科
  • 肿瘤标志物异常 → 肿瘤科
  • 多系统异常 → 全科(作为协调员)

第三步:并行启动专科分析

使用 Task 工具并行启动所有相关专科的 subagent:

// 示例:启动多个专科 subagent
Task("subagent_type", {
  description: "心内科分析",
  prompt: `您是心内科专家。请分析以下医疗数据:

${医疗数据内容}

请按照 .claude/specialists/cardiology.md 中定义的格式提供分析报告。

严格遵守以下安全红线:
- 不给出具体用药剂量
- 不直接开具处方药名
- 不判断生死预后
- 不替代医生诊断

请返回完整的分析报告。`
})

注意: 在单个响应中并行启动多个 Task,提高效率。

第四步:整合会诊意见

  1. 等待所有专科 subagent 完成分析
  2. 收集各专科的分析报告
  3. 按照 .claude/specialists/consultation-coordinator.md 中定义的格式整合报告
  4. 生成完整的多学科会诊(MDT)报告

第五步:输出报告

向用户展示完整的会诊报告,包括:

  • 各专科分析
  • 综合评估
  • 优先级排序
  • 综合建议
  • 随访计划
  • 重要声明

输入参数

用户可以通过以下方式调用:

# 分析所有数据
/consult all

# 分析最近N条记录
/consult recent 5

# 分析指定日期的数据
/consult date 2025-12-31

# 分析指定日期范围
/consult date 2025-12-01 to 2025-12-31

# 自动分析(默认最近3条)
/consult

安全红线(严格遵守)

在执行会诊过程中,必须确保:

  1. 不给出具体用药剂量

    • 错误示例:"服用阿托伐他汀 20mg 每日1次"
    • 正确做法:"建议咨询医生调整降脂药物方案"
  2. 不直接开具处方药名

    • 错误示例:"开具阿司匹林肠溶片"
    • 正确做法:"建议咨询医生是否需要抗血小板治疗"
  3. 不判断生死预后

    • 错误示例:"预后差,生存期不超过6个月"
    • 正确做法:"建议积极治疗,定期复查评估疗效"
  4. 不替代医生诊断

    • 错误示例:"确诊为冠心病"
    • 正确做法:"提示可能存在冠心病风险,建议心内科进一步检查明确诊断"

执行要求

  1. 并行处理:尽可能并行启动多个专科 subagent,提高效率
  2. 完整读取:确保读取完整的专科 skill 定义文件
  3. 格式统一:严格按照定义的报告格式输出
  4. 明确免责:每次会诊报告必须包含重要声明
  5. 可操作性:建议必须具体、可行

开始执行

现在,请按照上述流程,读取用户指定的医疗数据,启动多学科专家会诊,并生成完整的会诊报告。

记住:

  • 使用 Task 工具并行启动专科 subagent
  • 每个 subagent 读取对应的专科 skill 定义文件
  • 整合所有专科意见,形成综合报告
  • 严格遵守安全红线
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. yesterday First seen · 129 lines · 18 tokens per session scan A e0dbfca0eaf6

Subscribe to this mod's changes

consult is a command published in the GitHub repository huifer/WellAlly-health (935 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 1,128 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.