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 disco-trooper/skills --skill intervals-icugit clone --depth 1 https://github.com/disco-trooper/skillsWrote 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/disco-trooper/skills/intervals-icu)<a href="https://agentmods.dev/skills/disco-trooper/skills/intervals-icu"><img src="https://agentmods.dev/badge/skills/disco-trooper/skills/intervals-icu/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/disco-trooper/skills/intervals-icu"><img src="https://agentmods.dev/badge/skills/disco-trooper/skills/intervals-icu.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 | $0.00068 | $0.03338 |
| Opus 5.5 | $0.00027 | $0.01335 |
| Sonnet 5.5 | $0.00014 | $0.00668 |
| Haiku 4.5 | $0.00007 | $0.00334 |
Grade A, and why
intervals-icu scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **curl** - Pre-installed on most systems How it starts
The opening of the file, as written. The whole thing — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intervals.icu API Skill
Skill Relationship
┌─────────────────┐ fetch data ┌───────────────────┐
│ intervals-icu │ ──────────────────► │ cycling-training │
│ (DATA API) │ │ (ANALYSIS) │
│ │ ◄────────────────── │ │
│ • wellness │ interpret results │ • zone calc │
│ • activities │ │ • periodization │
│ • power curves │ │ • workout design │
│ • fitness │ │ • load management │
└─────────────────┘ └───────────────────┘
Usage pattern:
- Use
intervals-icuto fetch data from API - Use
cycling-trainingto analyze and interpret - Use
intervals-icuto update wellness/events
API wrapper for intervals.icu cycling training platform. Designed to work alongside the cycling-training skill.
Quick Start
# Set credentials (one-time)
export INTERVALS_API_KEY="your_api_key"
export INTERVALS_ATHLETE_ID="iXXXXX"
# Set skill directory for local installs
SKILLS_DIR="<path-to-your-skills-dir>"
# Use the API helper
"$SKILLS_DIR/intervals-icu/scripts/api.sh" wellness today
"$SKILLS_DIR/intervals-icu/scripts/api.sh" activities 2024-01-01 2024-01-31
Authentication
Get your API key from https://intervals.icu/settings → Developer Settings → API Key.
Find athlete ID in the URL when logged in: intervals.icu/athlete/iXXXXX/...
Rate Limiting
Intervals.icu API has rate limits. The script handles this with:
- Automatic retry with exponential backoff (default: 3 attempts)
- Configurable via
INTERVALS_MAX_RETRIESenvironment variable
# Increase retries for bulk operations
export INTERVALS_MAX_RETRIES=5
If you hit rate limits frequently:
- Add delays between bulk requests:
sleep 1 - Use date ranges instead of individual requests
- Cache responses locally for analysis
Prerequisites
- curl - Pre-installed on most systems
- jq -
brew install jq(macOS) /apt install jq(Linux) - bats-core - Optional, for tests:
brew install bats-core
What ships with it
7 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.
- 2mo ago First seen · 353 lines · 68 tokens per session scan A b359d4b4b42d
intervals-icu is a skill published in the GitHub repository disco-trooper/skills (6 stars, last pushed 4mo ago), licensed MIT. It adds 68 tokens to every session and 3,338 once invoked, about $0.0003 per session on Opus 5.5. 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.
intervals-icu compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| intervals-icudisco-trooper/skills | Skill | 6 | 4mo ago | MIT | A | 68 | Codex |
| strava-mcpdavidmosiah/strava-mcp | Skill | 3 | yesterday | MIT | A | 73 | Claude Code, Codex |
| stravadavidmosiah/strava-mcp | Skill | 3 | yesterday | MIT | A | 39 | Claude Code, Codex |
| stravaeddmann/strava-cli | Skill | 28 | 5mo ago | MIT | C | 44 | Claude Code, Codex |
| garmin-connecteddmann/garmin-connect-cli | Skill | 15 | 5mo ago | MIT | C | 45 | Claude Code, Codex |
| lambda-labs-gpu-cloudihatesea69/HieuNghi-AI-Skills | Skill | 3 | 8mo ago | MIT | C | 47 | Claude Code, Codex |
| pkf-writingPrismer-AI/PrismerCloud | Skill | 1.4k | 15d ago | MIT | A | 78 | Claude Code, Codex |