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/body-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/body-mcp-setup)<a href="https://agentmods.dev/skills/philipyaz/cos/body-mcp-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/body-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/body-mcp-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/body-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 | $0.00222 | $0.04964 |
| Opus 5 | $0.00111 | $0.02482 |
| Sonnet 5 | $0.00044 | $0.00993 |
| Haiku 4.5 | $0.00022 | $0.00496 |
Grade A, and why
body-mcp-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 9d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Body MCP setup (thin fetch-wrapper bridge :8012)
Why this exists / architecture
body is the foundational built-in add-on — the single owner of body identity (sex / date of
birth / height / training status / whether you lift), the weight + body-composition series, and the
free-text objective (the goal). Nutrition & Chef and Fitness both read it cross-add-on (current
weight, target, training status, the goal). Like nutrition and fitness, it has no external repo
and no sidecar: the server lives in this Cos checkout at mcp/body-server/server.mjs, the same
thin fetch wrapper archetype over the board's /api/body/* HTTP routes on CRM_BASE_URL. It makes
no LLM calls — the board serves deterministic physiology facts via /api/body/status (BMR / TDEE
/ BMI / trend / fat-free mass), but it never computes a recommendation; the daily targets are
authored by the agent (the nutrition-chef skill → save_nutrition_targets).
Every write is add-on-gated — attributed to the agent via the x-actor header and blocked only when the
add-on is disabled. 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
:8012($BODY_BRIDGE_PORT, labelcom.chiefofstaff.mcp-body, IN.mcp.json). - Claude Cowork Desktop spawns it as a direct stdio
commandentry inclaude_desktop_config.json.
Claude Code ──HTTP──> localhost:8012/mcp ──supergateway(launchd)──> node body-server (stdio)
│ fetch (x-actor:agent)
└──HTTP──> board /api/body/* (:3000)
Cowork Desktop ──spawns stdio directly──────────────────────────────────> node body-server (§5)
This add-on HARD AUTO-ENABLES — it is usually already on. Unlike nutrition/fitness (which ship disabled and need a manual toggle), body auto-enables in the same write whenever Nutrition or Fitness is enabled (a hard
dependsOncascade in/api/addons/[id]), because both consumers read body identity and are meaningless without it. So once you've enabled a consumer, body is on. It can also be enabled directly. Conversely, body refuses to be disabled (HTTP 409) while a hard consumer (Nutrition/Fitness) is still enabled — disable the consumer first. Its writes are GATED and its reads are open exactly like the other add-ons; a disabled body 404s every write (Not found.) and hides/404s the/bodypage.
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.
- 9d ago First seen · 275 lines · 222 tokens per session scan E 242a2ca302a5
body-mcp-setup is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 222 tokens to every session and 4,964 once invoked, about $0.0011 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 2026-08-31.
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…
opencode-plugin-idioms
Event hook payload shapes, session lifecycle timing, toast/TUI-route render boundaries, and child-session tagging conventions for OpenCode server (@opencode-ai/plugin) and TUI (@opencode-ai/plugin/tui) plugins, grounded in the vendored OpenCode source at references/opencode.
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…
self-align
Adversarial self-audit of the Kagan repo through four lenses — code quality & YAGNI, security, spec alignment, docs/AGENTS.md freshness — each finding self-assessed and reported by severity and confidence for the developer to action. Use only when explicitly asked to self-align, audit, or health-check the codebase; it…