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 ricardocabral/icuvisor --skill icuvisor-traininggit clone --depth 1 https://github.com/ricardocabral/icuvisorWrote 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/ricardocabral/icuvisor/icuvisor-training)<a href="https://agentmods.dev/skills/ricardocabral/icuvisor/icuvisor-training"><img src="https://agentmods.dev/badge/skills/ricardocabral/icuvisor/icuvisor-training/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/ricardocabral/icuvisor/icuvisor-training"><img src="https://agentmods.dev/badge/skills/ricardocabral/icuvisor/icuvisor-training.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 43 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00048 | $0.01078 |
| Opus 5 | $0.00024 | $0.00539 |
| Sonnet 5 | $0.00010 | $0.00216 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
icuvisor-training 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
icuvisor Training Skill
Use icuvisor MCP tools whenever the user asks about intervals.icu training data, fitness, wellness, activities, events, workouts, training plans, readiness, race prep, or calendar changes.
Grounding
- Ground training, wellness, calendar, workout, and fitness claims in icuvisor tool results or icuvisor MCP prompts.
- Cite the source tool or prompt behind key numbers, such as
get_today,get_athlete_profile,get_fitness,get_training_summary,get_activities,get_wellness_data,get_events,get_training_plan,compute_zone_time,compute_load_balance,analyze_trend,weekly_review,recovery_check, orrace_week_taper. - Prefer terse/default responses. Use
include_fullonly when the user asks for raw detail or terse output lacks the evidence needed. - Do not invent metrics, zones, HRV values, sleep values, load numbers, planned events, workouts, race details, or unavailable fields.
- If data is missing, stale, paginated, truncated, or unavailable, say so plainly before interpreting it.
Dates and Timezone
- Interpret "today", "tomorrow", "this week", "last week", weekdays, and race countdowns in the athlete-local timezone returned by icuvisor.
- For date-sensitive planning, call
resolve_calendar_datesbefore using relative dates or a user-supplied weekday/date pairing. - Use returned
as_of,as_of_date,as_of_weekday, andtimezonemetadata as freshness anchors. - If today's wellness or activity data has not synced, state the latest available date instead of guessing today's values.
Scales and Provenance
- Preserve scale labels exactly as icuvisor returns them.
- Sleep quality is 1-4. Feel is 1-5. RPE is 1-10.
- Do not rescale subjective values to 0-10 unless the source scale is already 0-10.
- When readiness, sleep, or wellness fields include provider-native provenance or stale flags, mention them if they affect the recommendation.
Writes and Safety
- Do not create, update, schedule, or delete anything unless the user explicitly asks for a write action.
- Before any write, summarize the intended change and ask for confirmation unless the client already provides a tool-approval confirmation that shows the exact operation.
- For destructive actions, verify that the relevant delete tool is visible and that the user explicitly requested deletion.
- If a write or delete tool is missing, explain that the current icuvisor safety mode or hosted preference does not expose it; offer a preview-only plan instead.
- Never ask the user to paste Intervals API keys, OAuth tokens, cookies, raw authorization headers, local config files, or secrets into chat.
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 · 74 lines · 48 tokens per session scan A 7ff747cb3f55
icuvisor-training is a skill published in the GitHub repository ricardocabral/icuvisor (29 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 1,078 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
baoyu-comic
A creator for educational comics, including biographies and tutorials, that turns supplied content or topics into illustrated comic pages.
canvas
Fetch Canvas LMS courses and assignments via API token.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
copilotkit-self-update
Use when the user wants to update, refresh, or reinstall the CopilotKit agent SKILLS (the SKILL.md files that teach this agent about CopilotKit). NOT for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit…
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
eli5
Explain concepts in very simple terms suitable for a five-year-old.