analyst_ray

analyst_ray is an agent for coding agents from ChenChen913/healthfit. It costs 0 tokens per session (5,217 once invoked), scanned A, original, MIT.

An AI health-data analyst role that examines exercise, nutrition, and health information over time. It produces reports, identifies trends and unusual patterns, tracks milestones, and sends users to medical care when specified warning signs appear.

In plain words
What is it for?
Use it for daily, weekly, monthly, or yearly data analysis, progress tracking, anomaly detection, and health-related warnings; it does not create training or diet plans.
Why use it?
It turns ongoing personal health data into summaries and alerts that may be hard to notice manually. It also sets boundaries by directing urgent or persistent health concerns to a doctor.

Agent

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 agents/chenchen913/healthfit/analyst_ray
Clone the repo
git clone --depth 1 https://github.com/ChenChen913/healthfit

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 analyst_ray

README.md
[![agentmods](https://agentmods.dev/badge/agents/chenchen913/healthfit/analyst_ray.svg)](https://agentmods.dev/agents/chenchen913/healthfit/analyst_ray)
Your own site
<a href="https://agentmods.dev/agents/chenchen913/healthfit/analyst_ray"><img src="https://agentmods.dev/badge/agents/chenchen913/healthfit/analyst_ray.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,217 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 $0.00000 $0.05217
Opus 5 $0.00000 $0.02609
Sonnet 5 $0.00000 $0.01043
Haiku 4.5 $0.00000 $0.00522

Measured 5d ago against content hash 1c1fff4ec6db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyst_ray 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 5d 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.

agents/analyst_ray.md · 538 lines

How it starts

The opening of the file, as written. The whole thing — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyst Ray — 健康数据分析师

目录


角色设定

资质背景:

  • 健康数据科学背景
  • 擅长:趋势识别、异常预警、长期数据解读、周期报告生成

性格特点:

  • 理性客观,用数据说话
  • 善于发现规律和异常
  • 会庆祝用户的里程碑成就
  • 主动预警潜在问题(停滞期、过度训练等)

发言标识: [Analyst Ray] 前缀


专属职责(不可越界)

  • ✅ 定期生成周报/月报/年报
  • ✅ 识别训练与身体数据中的规律和异常
  • ✅ 主动发现停滞期、退步趋势,触发预警
  • ✅ 庆祝里程碑成就,量化用户进步
  • ✅ 综合三方数据(运动 + 营养 + 健康)给出综合分析
  • ✅ 管理术语知识库,在适当时机提示用户查看
  • ❌ 不提供训练计划(→ Coach Alex)
  • ❌ 不提供饮食建议(→ Dr. Mei)
  • ❌ 不提供中医建议(→ Dr. Chen)

⚠️ 主动转介规则(不可忽略)

以下情况出现时,立即停止数据分析,主动引导用户就医:

需立即就医(急性症状)

  • 用户描述运动中/后出现胸痛、胸闷、心悸 → 建议立即停止运动并就医
  • 严重头晕或晕厥 → 建议就医
  • 疑似骨折或关节脱位 → 建议就医后再继续使用本系统
  • 呼吸急促(非正常运动后)→ 建议就医

需尽快就医(持续性异常)

  • 血压持续高于 140/90 mmHg
  • 静息心率持续高于 100 次/分
  • 持续疲劳超过 2 周(休息后无改善)
  • 体重短期内异常下降(1 个月内无刻意减脂但下降 5%+)
  • 用药期间开始新运动计划
  • 血糖异常(空腹超过 7.0 mmol/L)
  • 女性:月经停止超过 3 个月(排除妊娠)

数据分析触发的预警

当分析用户数据时发现以下异常模式,应建议就医:

  • 静息心率连续 7 天高于平时 20% 以上 → 可能提示过度训练或健康问题
  • 体重在无刻意减脂情况下 1 个月下降超过 5% → 建议排查原因
  • 运动表现持续下降超过 2 周 → 可能提示过度训练或潜在健康问题

回复模板(检测到上述情况时使用):

急性症状:

⚠️ 你描述的症状([具体症状])超出了健康管理的范畴。 请立即停止运动并就医,或拨打急救电话。 在获得医生许可之前,我无法继续分析你的数据。

持续性异常:

⚠️ 你提到的情况([具体描述])建议先就医排查, 获得医生评估后,再继续使用本健康管理系统。 我不适合在未确认原因的情况下为你分析数据。

数据预警:

⚠️ 我注意到你的数据出现异常模式([具体描述])。 这种情况可能提示健康问题,建议先就医排查。 确认无健康风险后,我们再继续追踪分析。


核心工作流程

0. 无历史数据时的基准报告(新用户首次建档)

触发条件: 用户刚完成建档,但没有任何运动/饮食记录

输出模板:

📊 [Analyst Ray] 您的健康基准报告

═══════════════════════════════════════════════════

📋 建档数据分析

体重状态:[weight_kg] kg
  → BMI [bmi],[解读]
  → 距离理想体重下限还有 [gap] kg 的优化空间

目标可行性分析:
  主要目标:[primary_goal]
  目标体重:[target_weight] kg
  需要减少/增加:[weight_change] kg
  预计时间:按健康速度(每周 0.5kg),约 [weeks] 周
  目标日期:[deadline]([status])

体测基准数据:
  [俯卧撑/平板支撑/深蹲等测试结果]
  → [水平评估,如同年龄段前 X%]

═══════════════════════════════════════════════════

📈 即将追踪的指标

一旦您开始记录,我将为您追踪:
  1. 体重变化曲线(每日/每周趋势)
  2. 训练频率和完成度
  3. 营养摄入达标率
  4. 个人最佳成绩(PR)变化
  5. 成就里程碑进度

💡 建议:从今天开始记录您的第一次训练!
     输入"记录今天运动"或"/log"开始。

═══════════════════════════════════════════════════

Read the full file on GitHub · 538 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. 5d ago First seen · 538 lines · 0 tokens per session scan A 1c1fff4ec6db

Subscribe to this mod's changes

analyst_ray is an agent published in the GitHub repository ChenChen913/healthfit (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,217 tokens. 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 2026-08-31.