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 philipyaz/cos --skill fitness-athlete-profilegit 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-athlete-profile)<a href="https://agentmods.dev/skills/philipyaz/cos/fitness-athlete-profile"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-athlete-profile/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-athlete-profile"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-athlete-profile.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 | $0.00251 | $0.03059 |
| Opus 5 | $0.00125 | $0.01529 |
| Sonnet 5 | $0.00050 | $0.00612 |
| Haiku 4.5 | $0.00025 | $0.00306 |
Grade A, and why
fitness-athlete-profile scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
through the **`fitness`** MCP — never `bash`/`curl` (Cowork's sandbox blocks outbound HTTP). The How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness — athlete profile (the coach's training-focus source of truth)
This skill owns the athlete profile: the one record (a singleton — one per board) that
says what sport/event the user is training for, with how much time, on which sports, with what
gear. The three generative coaching skills — training plan, weekly review, pre-workout
brief (all in fitness-coach) — read this profile to personalise everything. It writes only
through the fitness MCP — never bash/curl (Cowork's sandbox blocks outbound HTTP). The
/fitness overview page is the read twin.
The profile is create-or-REPLACE (set_athlete_profile overwrites the whole record;
createdAt is sticky). So the cardinal rule is: read first, then write the merged whole —
never send a partial that drops fields the user isn't changing.
This is the TRAINING half only — the BODY half lives elsewhere (v14). Your training STATUS (novice / intermediate / advanced), your weight + body composition, and your body goal (lose fat / build muscle / recomp / maintain — the free-text objective) are owned by the body add-on, NOT this profile. Set them via the
body-profileskill (or thebodyMCP:set_body_profilefor training status,log_weightfor weigh-ins,set_body_objectivefor the goal) or the /body page. This skill'sgoalis a training FOCUS — the sport or event — not the body objective. The coach reads training status + weight + the body goal cross-add-on; you don't set them here.
Gate — the add-on must be ENABLED.
set_athlete_profile404s ("Not found — the fitness add-on may be disabled.") when the Fitness add-on is disabled; the read (get_athlete_profile) always works. If the save 404s, the add-on is off — tell the user to enable it from the board's /addons catalog, then retry. You don't enable it yourself.
NOT MEDICAL ADVICE. Anything weight- or health-related is informational, not medical advice. Don't prescribe a weight or rate; defer medical conditions, pregnancy/breastfeeding, an eating-disorder history, or a user under 18 to a clinician or registered dietitian. The body goal
- weight live in the body add-on (
body-profile); the diet math (calorie/macro targets) lives in the Nutrition add-on (nutrition-chef).
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.
- 12d ago First seen · 171 lines · 251 tokens per session scan A 9ed320f36f5e
fitness-athlete-profile is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed 2d ago), licensed MIT. It adds 251 tokens to every session and 3,059 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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-boundary
Rank the "frontier" pages of a wiki — the crossroads many pages link to that stay thin inside — so you can decide where research would pay off most. Use when the user says "what should I write about next", "where are the gaps", "which pages need work", "find the thin hub pages", "boundary pages", "/wiki-boundary"…
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…