Borrowing it
Nothing to install: this file belongs to philipyaz/cos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/philipyaz/cos/main/.claude/skills/fitness-mcp-setup/SKILL.mdgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/fitness-mcp-setup)<a href="https://agentmods.dev/skills/philipyaz/cos/fitness-mcp-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-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/philipyaz/cos/fitness-mcp-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-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 | $0.00211 | $0.06670 |
| Opus 5.5 | $0.00084 | $0.02668 |
| Sonnet 5.5 | $0.00042 | $0.01334 |
| Haiku 4.5 | $0.00021 | $0.00667 |
Grade E, and why
fitness-mcp-setup scanned grade E with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X PATCH "$BOARD_URL/api/addons/fitness" -H 'Content-Type: application/json' -d '{"enabled":false}' ; echo Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -s "$BOARD_URL/api/addons" | node -e 'let s="";process.stdin.on("data",d=>s+=d).on("end",()=>{const a=JSON.parse(s).addons.find(x=>x.id==="fitness");process.exit(a&&a.enabled===true?0:1)})' && echo "add-on enabled" Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
grep -q '"fitness"' "$REPO_ROOT/.mcp.json" && echo ".mcp.json fitness entry OK" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$FITNESS_BRIDGE_URL/mcp" \ How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness MCP setup (thin fetch-wrapper bridge :8011)
Why this exists / architecture
fitness is the second built-in add-on ("Fitness" — Apple Watch health ingestion +
dashboard at /fitness/health, plus the athlete training profile + AI coach at /fitness). Like
nutrition, it has no external repo and no sidecar: the server lives in this Cos checkout
at mcp/fitness-server/server.mjs, and it is the same thin fetch wrapper archetype over the
board's /api/fitness/* HTTP routes on CRM_BASE_URL. It makes no LLM calls — the coaching
intelligence (training plans, weekly reviews, pre-workout briefs) lives on the board's /api/fitness/*
routes (server-side Claude calls) and in the operator skill (/fitness-coach), not here.
Like nutrition, every write is add-on-gated — attributed to the agent via the x-actor header
and blocked only when the add-on is disabled. The Apple-Watch ingest endpoint
(POST /api/fitness/push) is the same: the MCP's push_health_data lands a batch of canonical
entries, gated by the add-on toggle exactly like every other write.
It is a single Node stdio process and registers into Cos the same two ways the core servers do:
- Claude Code reaches it over HTTP via a supergateway + launchd BRIDGE on
:8011($FITNESS_BRIDGE_PORT, labelcom.chiefofstaff.mcp-fitness, IN.mcp.json). - Claude Cowork Desktop spawns it as a direct stdio
commandentry inclaude_desktop_config.json— identical to how mcp-bridge-setup wires board/calendar/etc.
Claude Code ──HTTP──> localhost:8011/mcp ──supergateway(launchd)──> node fitness-server (stdio)
│ fetch (x-actor:agent)
└──HTTP──> board /api/fitness/* (:3000)
Cowork Desktop ──spawns stdio directly──────────────────────────────────> node fitness-server (§5)
This is an ADD-ON — its WRITES are GATED, its READS are open. The "Fitness" add-on must be ENABLED (
Settings.addons.fitness.enabledincases.json) for writes to land. A disabled add-on 404s every write (the board surfaces it here as aNot found — the fitness add-on may be disabled.tool error) while every GET read stays open, and its/fitness+/fitness/*nav pages 404 + hide. Enabling is itself a step (§6) — flip it from the board's/addonscatalog (orPATCH /api/addons/fitness).
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.
- 1mo ago Changed · +1 lines 2ac70004f9fb
- 1mo ago First seen · 351 lines · 211 tokens per session scan E 8887c52f6b60
fitness-mcp-setup is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed 2d ago), licensed MIT. It adds 211 tokens to every session and 6,670 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it E with 4 findings (sends data to an external url, downloads and executes remote code, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
pulse
Weekly read of what is actually getting built or done, per work-block — from the tracker, the code, and the docs. State of the work, not the stream of events. Distinct from the digest, which is signal since the last run.
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-export
Export a vault's wiki either as a single portable file (llms.txt or llms-full.txt per the llmstxt.org standard) or as an OKF knowledge bundle (Google's Open Knowledge Format v0.1 — a shareable directory of markdown files any AI agent can consume). Use when the user says "export my wiki", "make an llms.txt", "share my…
wiki-query
Answer a question using ONLY the existing wiki vault as the knowledge base — no web search, no general LLM knowledge. Reads hot.md first (cheap recent context), then catalog.md to navigate, then drills into specific pages, then optionally semantic-searches the wiki, and synthesizes an answer with citations. Use when…