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/todaynpx skills add rlacombe/switchback-running --skill todaygit 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 | $0.00012 | $0.00608 |
| Opus 5 | $0.00006 | $0.00304 |
| Sonnet 5 | $0.00002 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
today 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 3d 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.
What it actually says
/today — Morning Briefing
- Get today's date. Read
knowledge/recovery-overtraining.mdfor overtraining warning signs andknowledge/workout-types.mdfor workout execution guidance.- If Intervals.icu is unavailable, use recent Strava activity history and the athlete profile for a limited briefing. State that planned workouts, wellness, fitness, and calendar data are unavailable rather than fabricating them.
- Fetch data using MCP tools (call them directly, in parallel where possible):
- Events endpoint for the next 14 days (oldest=today, newest=today+13) — today's workout plus the full training block ahead for context
- Wellness endpoint for the last 3 days (oldest=today-2, newest=today) — trend context, not just a snapshot
- Fitness endpoint for the last 7 days to show trend
- Weather endpoint using the athlete's lat/lon from their profile — current conditions and forecast
- Zones are cached in
athlete/profile.md— skip the athlete endpoint unless the zones section is missing
- Display:
- Today's Workout: Name, type, planned distance/duration. If the workout has structured steps, show target zones/paces using the athlete's actual zone values. If rest day, say so.
- This Week / Next Week: Brief overview of the 2-week plan ahead — session names, days, types. Highlight the training block context (build week? recovery week? race week?) so today's workout makes sense in the bigger picture.
- Wellness: Sleep, HRV, resting HR, fatigue, mood (whatever is available)
- Form Status: Current TSB with label (fresh/neutral/tired/fatigued)
- CTL/ATL: Current values and 7-day trend direction
- Weather: Current conditions and today's forecast (temp, feels-like, wind, precipitation, UV). Flag heat/cold/rain concerns that affect the workout — suggest timing adjustments, hydration, or gear.
- Check data freshness. Look at today's wellness
updatedtimestamp. If it's more than 1 hour old (or missing entirely), warn the athlete that their device may not have synced recently — wellness and fitness numbers may be stale. Suggest they open Garmin Connect (or their watch app) to trigger a sync, then ask you to re-run/today. Keep the warning brief: one line, not a blocker. - End with a one-line recommendation grounded in the knowledge base (e.g., reference workout purpose from
knowledge/workout-types.md, or flag recovery concerns perknowledge/recovery-overtraining.md) - Flag any injury risk signals (volume spike, sustained negative TSB, poor sleep) using criteria from
knowledge/injury-prevention.md
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.
- 3d ago First seen · 26 lines · 12 tokens per session scan A f9942bc92f2e
today is a skill published in the GitHub repository rlacombe/switchback-running (11 stars, last pushed 8d ago), licensed MIT. It adds 12 tokens to every session and 608 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…
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
wiki-manager
Manage LLM-compiled wikis: initialize, ingest/import, compile/query, research/audit, collect catalogs, track inventory/datasets/Ideas, review Idea/Project portfolios, manage archives/sessions/feedback, and generate outputs. Activates for /wiki commands; wiki or knowledge-base work; ingest, collect, catalog, compile…
unity-vrc-skills-renovator
VRChat skill renovator for knowledge fill, refresh, and quality improvement. Use this skill when updating VRChat skills to new SDK versions, filling missing knowledge, fixing outdated information, or improving skill quality. Targets unity-vrc-udon-sharp and unity-vrc-world-sdk-3 skills. Triggers on: update skills, SDK…