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-correlationsgit 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-correlations)<a href="https://agentmods.dev/skills/philipyaz/cos/fitness-correlations"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-correlations/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-correlations"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/fitness-correlations.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 | $0.00209 | $0.02104 |
| Opus 5 | $0.00105 | $0.01052 |
| Sonnet 5 | $0.00042 | $0.00421 |
| Haiku 4.5 | $0.00021 | $0.00210 |
Grade A, and why
fitness-correlations 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 10d 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.
health-data plumbing runs **only** through the **`fitness`** MCP — never `bash`/`curl`. How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness correlations (the sleep ↔ performance interpreter)
This skill answers "how does my sleep affect my performance?" It is the interpret
half of a deterministic compute: the board computes the statistics (Pearson r for
sleep-vs-performance and deep-sleep-vs-performance, plus a linear regression) — you do
not. The board is a state machine; the math is the board's, the meaning is yours.
There is no board-side LLM here either — get_correlations runs pure, repeatable stats
and persists the snapshot; your job is to trigger that compute via the fitness MCP,
then read the numbers back to the user in plain language with actionable guidance. The
health-data plumbing runs only through the fitness MCP — never bash/curl.
This skill mostly READS + interprets. It does not usually write — get_correlations
already computes and persists the snapshot, so you almost never call save_correlation_report
(that writer is for an externally-computed dataset the user supplies — see the guardrail).
NOT MEDICAL ADVICE — and NOT causation. A correlation between sleep and performance is an observational association across your logged data, not proof that sleep causes the performance change — say so, in your own words. And it is informational, not medical advice: defer any injury, illness, abnormal symptom, pregnancy, or an under-18 user to a physician / physiotherapist / qualified coach; don't push hard training off a number.
Gate.
get_correlationsis a read/compute — it works whether or not the Fitness add-on is enabled (reads are always open). The persist it does is add-on-gated: it lands when the add-on is enabled and is skipped (404) when it's off — tell the user to enable it at /addons if you need the snapshot to stick.
PROCEDURE — compute (board), then interpret (you)
1. COMPUTE — get_correlations({ days }) (the board's deterministic stats)
Call get_correlations with the window the user asked for:
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.
- 10d ago First seen · 141 lines · 209 tokens per session scan A 6d034886fb69
fitness-correlations is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 209 tokens to every session and 2,104 once invoked, about $0.0010 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-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-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"…