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 AntVsl/oura_mcp --skill ouragit clone --depth 1 https://github.com/AntVsl/oura_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/antvsl/oura_mcp/oura)<a href="https://agentmods.dev/skills/antvsl/oura_mcp/oura"><img src="https://agentmods.dev/badge/skills/antvsl/oura_mcp/oura/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/antvsl/oura_mcp/oura"><img src="https://agentmods.dev/badge/skills/antvsl/oura_mcp/oura.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 | $0.00075 | $0.00941 |
| Opus 5 | $0.00037 | $0.00470 |
| Sonnet 5 | $0.00015 | $0.00188 |
| Haiku 4.5 | $0.00007 | $0.00094 |
Grade A, and why
oura 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oura
Client-neutral workflows for my-oura-mcp. The server exposes eleven tools;
this skill covers what to do with them beyond a single call. Confirm that the
MCP server is connected with get_status before relying on its data.
What the tools already handle
Worth knowing, because it changes what you have to think about:
- Answers arrive compressed. Every tool returns per-day values plus
statswith mean, min, max and — when there are at least four days —trend_per_week. You do not need to average anything by hand, and there is no pagination to manage. - Timezones are resolved server-side from
OURA_TZ. Never convert to UTC yourself. "Today" already means the user's today, night sleep is already attributed to the right calendar day, and heart rate is already grouped by local day. - Naps are separated from the main night.
get_sleepreports the main sleep and puts anything else innaps_h.
Pass raw=True to any tool for the untouched API response. Only worth it when a
field is missing from the summary — it is a lot of tokens.
Choosing a window
Every ranged tool takes either days_back or an explicit start_date /
end_date pair in YYYY-MM-DD. Explicit dates win if both are given.
Resolve vague phrasing before calling:
| Phrase | Window |
|---|---|
| «за неделю», "last week", "past week" | days_back=7 |
| «за две недели», "last two weeks" | days_back=14 |
| «за месяц», "last month" | days_back=30 |
| «вчера», "yesterday" | start_date = end_date = yesterday |
| «сегодня», "today" | days_back=1 |
If the user names no period at all, seven days is the sensible default — except where a recipe below says otherwise, in which case follow the recipe.
trend_per_week only appears with four or more days of data. A three-day window
gives you no trend, so do not promise one.
Tools
| Tool | Answers |
|---|---|
get_daily_summary |
sleep, readiness and activity scores together |
get_sleep |
stages, efficiency, HRV, resting heart rate, breathing, temperature |
get_sleep_score |
just the nightly score — lighter than get_sleep |
get_readiness |
readiness, HRV balance, temperature deviation |
get_activity |
steps, calories, activity score |
get_heartrate |
heart rate grouped by local day |
get_stress |
daytime stress and recovery time |
get_spo2 |
blood oxygen and breathing disturbance |
get_heart_health |
cardiovascular age and VO₂ max |
get_tags |
the user's own notes and markers |
get_status |
whether the server has real data or sandbox data |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 83 lines · 75 tokens per session scan A b8b0f7f57eb4
oura is a skill published in the GitHub repository AntVsl/oura_mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 75 tokens to every session and 941 once invoked, about $0.0004 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
health
Personal health knowledge graph — local-first ingest of Garmin (Apple Health, Whoop, Oura, CGM in v2+) traces into SQLite, projected to Obsidian daily-note frontmatter, synthesized into validated longevity-proxy metrics (HRV-CV, CTL/ATL/TSB, VO2max arc). Hex architecture so new sources drop in as adapters. NOT a…
tiaportal-mcp
A skill for controlling Siemens TIA Portal, the engineering software used to configure Siemens PLCs and HMIs. It works through an MCP server, a tool connection that lets an agent inspect and change projects.
asset-management
Manage ServiceNow hardware assets, software licenses, and lifecycle states on almhardware/almlicense — license allocation, CMDB-to-asset linking, warranty tracking, inventory aggregation (HAM/SAM).
kernelcad-assemblies
Multi-part assemblies — assembly(), parts, connectors, 7 mate types, fixed and revolute joints, .model()/.solvedModel(). Use for any model with two or more mechanical parts that need joint metadata.
kernelcad-kinematic
Use when verifying whether a moving assembly is buildable — sampled-pose collision sweeps across joint ranges, IK reachability for end-effector targets, mounting-hole fastener consistency, and static-load capacity on cantilever-shaped parts. Loads alongside kernelcad-authoring to gate design-time mechanism feasibility.
kernelcad-parts
Bundled parts catalog — discover, fetch, and mate standard fasteners, bearings, motors, headers, and connectors. Use whenever the model needs an off-the-shelf component instead of hand-modeled placeholder geometry.