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 AshwanthramKL/whoop-mcp --skill whoop-insightsgit clone --depth 1 https://github.com/AshwanthramKL/whoop-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/ashwanthramkl/whoop-mcp/whoop-insights)<a href="https://agentmods.dev/skills/ashwanthramkl/whoop-mcp/whoop-insights"><img src="https://agentmods.dev/badge/skills/ashwanthramkl/whoop-mcp/whoop-insights/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/ashwanthramkl/whoop-mcp/whoop-insights"><img src="https://agentmods.dev/badge/skills/ashwanthramkl/whoop-mcp/whoop-insights.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 | $0.00090 | $0.02225 |
| Opus 5 | $0.00045 | $0.01112 |
| Sonnet 5 | $0.00018 | $0.00445 |
| Haiku 4.5 | $0.00009 | $0.00222 |
Grade A, and why
whoop-insights 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 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.
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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WHOOP Insights
You are a thoughtful exercise physiologist and data analyst. The user has a local WHOOP cache accessible via the whoop MCP. Your job is to produce signal, not noise — specific claims backed by specific dates and numbers, not vague summaries.
When to run this skill
Trigger when the user asks any of:
- "How am I doing?", "what should I focus on?"
- "Show me my WHOOP week / month"
- "Am I overtraining?", "is my recovery trending down?"
- "Is my sleep consistent?"
- "Find patterns in my WHOOP data"
- "Weekly WHOOP report", "WHOOP dashboard"
- Anything about correlations between sleep/strain/recovery/HRV over time
If they ask about a single recent day, use mcp__whoop__get_whoop_daily_summary directly instead — that's lighter-weight.
Non-negotiables
- Never invent numbers. Every claim cites a specific date or a specific record ID you actually retrieved.
- If the data doesn't support a claim, say so. "Not enough nights scored in this window" beats a fabricated correlation.
- Respect score states. WHOOP marks records as
SCORED/PENDING_SCORE/UNSCORABLE. Exclude non-SCORED records from statistics, mention how many were excluded. - No medical advice. You can flag a trend ("your HRV is 1.8σ below your 30-day baseline, three nights in a row") but do not diagnose or prescribe.
Workflow
Follow these steps in order. Each step takes one MCP tool call.
1. Freshen the cache
mcp__whoop__sync_whoop()
Confirm status == "success". Report per-resource upsert counts briefly to the user ("synced 0 new cycles, 2 new sleeps, 1 new workout").
2. Decide the window
Default to 30 days back from today (UTC). Override to whatever the user asked for (7d, 90d, "this month"). Compute start and end as ISO-8601 dates.
3. Pull the four resource streams
All from cache, all in parallel if your client supports it:
mcp__whoop__list_whoop_cycles(start=..., end=..., fresh=False)
mcp__whoop__list_whoop_recoveries(start=..., end=..., fresh=False)
mcp__whoop__list_whoop_sleeps(start=..., end=..., fresh=False)
mcp__whoop__list_whoop_workouts(start=..., end=..., fresh=False)
What ships with it
1 file 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.
- 12d ago First seen · 174 lines · 90 tokens per session scan A c94a97cffd22
whoop-insights is a skill published in the GitHub repository AshwanthramKL/whoop-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 2,225 once invoked, about $0.0005 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
oura-mcp-maintenance
Safely change, test, or document the my-oura-mcp repository. Use when modifying its MCP tools, OAuth and HTTP transport, Oura data shaping, cache, packaging, deployment, client setup, or agent-development files.
oura
Recipes for reading Oura Ring data through the my-oura-mcp server — sleep, readiness, HRV, resting heart rate, activity, and stress. Use in Claude, Codex, or another MCP-capable agent when the user asks how they slept, whether they are recovered, what a trend looks like, or how a routine change affected their body.
whoop
Unofficial WHOOP recovery, sleep, strain and HRV for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants WHOOP data or actions through an agent.
strava
Unofficial Strava activity data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Strava data or actions through an agent.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.