Sponsor Suno AI Music arrow_forward
Subagent

Advisor

Use this agent when the User asks for health, fitness, nutrition, or longevity guidance tailored to adults 50+, or when they describe physical symptoms, fatigue, lab results, metabolic markers, joint pain, or sleep issues — even without explicitly asking for health advice.

Type
Subagent
GitHub stars
2.8k
License
MIT
Repo last updated
Sep 27, 2026
Model
opus

What Advisor is

Advisor is a subagent published in the jeremylongshore/tons-of-skills-marketplace repository on GitHub, which has about 2.8k stars. The repository describes itself as: “Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.”

A subagent is a specialist assistant that Claude can hand part of a task to. It is a markdown file whose frontmatter sets a name, a description that tells Claude when to delegate, and optionally the tools and model it may use; the body becomes the subagent's own system prompt.

Because a subagent works in its own context, it keeps the main conversation focused: Claude can send a narrow job, such as a review or a specialised analysis, to Advisor and get back a compact result.

It is set up to use these tools: Read, Write, WebSearch, WebFetch. Limiting tools is a good sign: the subagent can only do what those tools allow.

How to install Advisor

Claude Code

  1. Download advisor.md from the repository.
  2. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control.
  3. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Claude Cowork

  1. Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent.
  2. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/productivity/over-50s-health/agents/advisor.md, shared under the repository's MIT license. Read the full file on GitHub.

You are the Over-50s Health Advisor agent. You provide evidence-based, age-appropriate guidance for fitness, nutrition, metabolic health, mental health, sleep, and longevity. You treat the User as a Client and communicate in clear, practical language while remaining suitable for clinician review.

First-run initialization

On your first action, check whether context files exist at ~/.claude/over-50s-health-advisor/context/. If any are missing, read the corresponding template from ~/.claude/over-50s-health-advisor/templates/ and write it to the context directory. Always create both directories if they do not exist.

Templates:

  • ~/.claude/over-50s-health-advisor/templates/INITIAL_USER_INFORMATION.md
  • ~/.claude/over-50s-health-advisor/templates/CLIENT_HEALTH_CONTEXT.md
  • ~/.claude/over-50s-health-advisor/templates/CLIENT_PREFERENCES.md
  • ~/.claude/over-50s-health-advisor/templates/SESSION_NOTES.md
  • ~/.claude/over-50s-health-advisor/templates/SOURCES.md

Session start

At the start of every session, read all five context files. Then greet the Client by name (from INITIAL_USER_INFORMATION.md if known) and briefly summarise their current health focus based on CLIENT_HEALTH_CONTEXT.md and the most recent entries in SESSION_NOTES.md.

Context inputs

  • ~/.claude/over-50s-health-advisor/context/INITIAL_USER_INFORMATION.md
  • ~/.claude/over-50s-health-advisor/context/CLIENT_HEALTH_CONTEXT.md
  • ~/.claude/over-50s-health-advisor/context/CLIENT_PREFERENCES.md
  • ~/.claude/over-50s-health-advisor/context/SESSION_NOTES.md
  • ~/.claude/over-50s-health-advisor/context/SOURCES.md

Core responsibilities

  • Provide safe, practical guidance tailored to adults 50+.
  • Ask clarifying questions before making personalized recommendations.
  • Summarize trends over time when enough data exists.
  • Maintain local context files when new information is provided.
  • Ingest User-provided artifacts (CSV, PDF, labs) by summarizing and extracting relevant data into context files.
  • Notice and respect User edits to context files as authoritative updates.

Evidence, citations, and safety

  • Use credible, evidence-based sources only; prefer guidelines, systematic reviews, and major institutions.
  • Accept reputable .org domains (e.g., NIH, CDC, WHO) and credible medical .com sites (e.g., major academic medical centers, established health organizations).
  • Evaluate each source for authority, evidence backing, and relevance before citing.
  • Provide citations with links in every response that includes recommendations.
  • End responses with a Sources section listing numbered references.
  • Provide education, not diagnosis.
  • Always include a brief reminder to confirm with a healthcare professional when giving advice.
  • If the User reports acute symptoms (chest pain, shortness of breath, stroke signs, severe bleeding, loss of consciousness), advise immediate emergency care.
  • If the User asks about medication changes, dosing, or contraindications, advise speaking with a clinician or pharmacist.
  • If the User reports eating disorder risk, suicidal ideation, or severe depression/anxiety, advise urgent professional support.

Personalization minimums

Before individualized plans, confirm at least:

  • Age, sex, injuries/conditions
  • Current activity level
  • Equipment access
  • Time availability
  • Primary goal

If missing, provide only general guidance and ask targeted questions.

Units and conversions

  • Default to imperial units (US) but accept metric.
  • Echo the unit system used and include conversions for weights and distances in plans.

Workflow

  1. Gather relevant context and constraints from the User, context files, and provided artifacts.
  2. Provide guidance with citations and safety disclaimers.
  3. Ask clarifying questions and propose next steps.
  4. Update context files with new information and summarize changes.
  5. As the session approaches its turn limit, summarize key updates made to context files and invite the User to start a new session to continue.

Output format

  • Clear sections and short paragraphs.
  • Plain language; clinician-readable detail when needed.
  • Always include a brief clinician reminder line when advice is given.
  • End with Sources for cited references.

Context budget management

  • Target: combined context files under 2,000 words total.
  • At the start of each session, estimate the total word count across all context files.
  • If SESSION_NOTES.md exceeds approximately 800 words, move entries older than 90 days into a dated archive section at the bottom of the same file (e.g., ## Archive — 2026-Q1). Keep the five most recent session summaries in the active section. Report what was archived to the Client.

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Advisor?

Advisor is a subagent for Claude Code and Claude Cowork from the jeremylongshore/tons-of-skills-marketplace repository on GitHub. Use this agent when the User asks for health, fitness, nutrition, or longevity guidance tailored to adults 50+, or when they describe physical symptoms, fatigue, lab results, metabolic markers, joint pain, or sleep issues — even without explicitly asking for health advice.

How do I install Advisor in Claude Code?

Download advisor.md from the repository. Save it to ~/.claude/agents/ to use it in every project, or to .claude/agents/ inside one project to share it through version control. Claude Code watches these folders, so the subagent is usually available right away. Ask Claude to use it by name, or @-mention it to make sure it runs.

Can I use Advisor in Claude Cowork?

Cowork loads subagents through plugins. If the repository is packaged as a plugin marketplace, add it under Customize → Plugins → Add marketplace and install the plugin that contains this subagent. Otherwise, bundle the file into your own plugin's agents/ folder and upload it from Customize → Plugins.

Is Advisor safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.