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 skills add turnnoblindeye/wellness-project-mcp --skill setupgit clone --depth 1 https://github.com/turnnoblindeye/wellness-project-mcpWrote 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.
[](https://agentmods.dev/skills/turnnoblindeye/wellness-project-mcp/setup)<a href="https://agentmods.dev/skills/turnnoblindeye/wellness-project-mcp/setup"><img src="https://agentmods.dev/badge/skills/turnnoblindeye/wellness-project-mcp/setup/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.
<a href="https://agentmods.dev/skills/turnnoblindeye/wellness-project-mcp/setup"><img src="https://agentmods.dev/badge/skills/turnnoblindeye/wellness-project-mcp/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.00567 |
| Opus 5 | $0.00030 | $0.00283 |
| Sonnet 5 | $0.00012 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
setup 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connecting Wellness Project
The plugin bundles one remote MCP server, wellness-project, pointed at
https://wellnessproject.ai/api/mcp. It needs a Wellness Project account and an
OAuth authorization before any tool returns data. Walk the user through the two
steps below in order.
1. Account and health sources
Tools read only what the user's account already holds, so an empty account returns empty results rather than an error.
Tell the user to:
- Create a free account at https://wellnessproject.ai.
- Open Settings → Devices and connect the sources they want: Apple Health, Google Health Connect, Fitbit, or Oura.
Manual logging works without any device connected, so a user who only wants to log workouts and meals by chat can skip step 2.
2. Authorize the connection
Run /mcp, select wellness-project, and choose to authenticate. Claude Code
registers itself dynamically and opens a browser for the Wellness Project OAuth
consent screen. No client ID, client secret, API key, or environment variable is
required.
After the user approves, /mcp shows the server as connected and its tools
become available.
Verifying
Call a cheap read tool and check that it returns the user's own data, for
example list_workouts for the last 7 days or list_body_metrics for the last
30 days. An empty result means the account has nothing logged for that range,
not that the connection failed.
Troubleshooting
- Tools missing after install: MCP servers register when the plugin loads.
Restart Claude Code, then re-run
/mcp. - 401 or "Unauthorized": the OAuth grant expired or was revoked. Re-run
/mcpand re-authenticate. - Connected but every read is empty: no health source is connected and nothing has been logged. Return to step 1.
- Revoking access: the user can revoke the connection from Wellness Project account settings at any time.
Scope
Every tool is scoped to the signed-in user's own account and enforced by row-level security. The catalog of tools is in TOOLS.md and the machine-readable schemas are in catalog/tools.json.
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.
- 4d ago First seen · 63 lines · 60 tokens per session scan A 2896fde00092
setup is a skill published in the GitHub repository turnnoblindeye/wellness-project-mcp (2 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 567 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
computer-use
Drive the desktop background-first; escalate on signal.
google-workspace
Gmail, Calendar, Drive, Docs, Sheets via gws CLI or Python.
simplify-code
Parallel 4-agent cleanup of recent code changes.
himalaya
Himalaya CLI: IMAP/SMTP email from terminal.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.