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 agentmods add skills/rlacombe/switchback-running/checknpx skills add rlacombe/switchback-running --skill checkgit clone --depth 1 https://github.com/rlacombe/switchback-runningWhat 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 | $0.00015 | $0.00807 |
| Opus 5 | $0.00008 | $0.00404 |
| Sonnet 5 | $0.00003 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
check 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 2d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/check — Health & Readiness Audit
Goes deeper than /today's daily snapshot. Analyzes multi-week trends to flag overtraining risk, volume ramp issues, recovery adequacy, and injury warning signs.
If only Strava is configured, limit the audit to completed-activity volume, frequency, intensity, and athlete-reported descriptions. Do not claim HRV, sleep, CTL/ATL/TSB, or planned-workout compliance without Intervals.icu data.
Step 1: Read knowledge base
Read these coaching files for detection criteria and thresholds:
knowledge/recovery-overtraining.md— FOR/NFOR/OTS stages, detection methods, warning signsknowledge/injury-prevention.md— red flags, volume ramp limits, return protocolsknowledge/volume-progression.md— 10% rule, build:recovery ratios, CTL ramp ratesknowledge/age-gender.md— age/gender-specific recovery considerations
Step 2: Gather data
Fetch data using MCP tools (call them directly, in parallel where possible):
- Wellness endpoint for the last 30 days — sleep, HRV, resting HR, fatigue, mood trends
- Fitness endpoint for the last 30 days — CTL/ATL/TSB progression
- Activities endpoint for the last 30 days — actual volume, frequency, intensity
- Events endpoint for the last 30 days — planned vs completed (compliance)
Read
athlete/profile.mdfor injury history, age, known weaknesses, and cached zones.
Step 3: Analyze
Volume Trends
- Weekly mileage progression over 4 weeks — flag increases >10%/week
- CTL ramp rate — flag if >5 points/week sustained
- Are recovery weeks happening? Check for step-back every 3-4 weeks
- Build:recovery ratio — is it 3:1 or 2:1? Should it be?
Wellness Trends
- HRV trend: declining over 7+ days = concern
- Resting HR trend: rising over 7+ days = concern
- Sleep: average over 30 days, trend direction, any sustained <7h periods
- Fatigue/mood: worsening trend over 7+ days
Overtraining Risk Assessment
Using the FOR → NFOR → OTS framework from knowledge/recovery-overtraining.md:
- Steve House's 3 warning signs: slow warmup, poor sleep, suspected injury (2+ = immediate rest)
- Performance decline: are recent workouts showing pace/HR regression?
- Compliance: missed workouts may indicate fatigue-driven avoidance
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.
- 2d ago First seen · 79 lines · 15 tokens per session scan A 21f61fc79cb8
check is a skill published in the GitHub repository rlacombe/switchback-running (11 stars, last pushed 7d ago), licensed MIT. It adds 15 tokens to every session and 807 once invoked, about $0.0001 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
platform-api
Queries the Genesys Cloud Platform API schema for endpoint details, permissions, parameters, and response formats. Use when user asks about Genesys Cloud API endpoints (e.g., "/api/v2/assistants/queues"), API documentation, API permissions, schemas, capabilities, or when implementing Genesys Cloud operations.
google-adk-python
Build production-ready AI agents in Python using Google Agent Development Kit (ADK). Use when creating agentic Python applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), multi-agent orchestration, tool development (function tools, MCP, OpenAPI), session and state management…
google-adk-typescript
Build production-ready AI agents in TypeScript using Google Agent Development Kit (ADK). Use when creating agentic TypeScript/JavaScript applications with LlmAgent, workflow agents (SequentialAgent, ParallelAgent, LoopAgent), custom agents (BaseAgent with runAsyncImpl), FunctionTool with Zod schemas, MCP and OpenAPI…
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
wiki-query
Fast, read-only, index-first llm-wiki queries for OpenCode and compatible instruction-file harnesses.