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/whynpx skills add rlacombe/switchback-running --skill whygit 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 | $0.00014 | $0.00584 |
| Opus 5 | $0.00007 | $0.00292 |
| Sonnet 5 | $0.00003 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
why 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/why — Training Science Explained
The athlete asks about any training concept, workout choice, or decision. Read the relevant knowledge base files, present expert positions, and connect the science to the athlete's situation.
Examples:
/why VO2max intervals/why am I running so slow on easy days/why weighted hiking for muscular endurance/why reverse periodization/why should I taper two weeks out
Step 1: Identify the topic
Map the athlete's question to the relevant knowledge base file(s) in knowledge/:
- aerobic-base.md, volume-progression.md, workout-types.md, muscular-endurance.md
- strength-training.md, periodization.md, long-runs.md, taper.md
- race-execution.md, recovery-overtraining.md, heat-altitude.md, mental-performance.md
- nutrition.md, downhill-training.md, injury-prevention.md, age-gender.md
Read the relevant file(s). If the question spans multiple topics, read all of them.
Step 2: Gather athlete context (if relevant)
If the question relates to the athlete's current training, use MCP tools to personalize the explanation:
- Zones are cached in
athlete/profile.md— use those to reference actual numbers - Fitness endpoint — their current CTL/ATL/TSB
- Activities or events endpoint — recent training context
Skip this step if the question is purely conceptual (e.g., "what is ADS?").
Step 3: Explain
Structure the response as:
- The concept — What it is and why it matters, in plain language
- What the experts say — Present each expert's position with their reasoning:
- Scott Johnston's view and logic
- Jason Koop's view and logic
- Steve Magness's view and logic
- Where they agree — Common ground
- Where they disagree — The tension, presented fairly with both sides
- What this means for you — Connect to the athlete's actual data, goals, and current training phase. If approaches conflict, explain which might fit their situation and why — then let them choose.
Guidelines
- Lead with the science, not opinions
- Use the athlete's actual zones and data when available — "your AeT is at 145bpm" is better than "your aerobic threshold"
- When experts disagree, present both sides honestly. Don't pick a winner unless the athlete's data clearly favors one approach
- Keep it conversational, not like a textbook
- Include key quotes from the experts — they carry weight
- If the athlete's question reveals a misconception, address it directly but respectfully
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 · 57 lines · 14 tokens per session scan A c9e7b4db45a2
why is a skill published in the GitHub repository rlacombe/switchback-running (11 stars, last pushed 7d ago), licensed MIT. It adds 14 tokens to every session and 584 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
openevidence
Query OpenEvidence (clinical evidence assistant) without an MCP server. Closely mirrors the openevidence-mcp tool surface - check auth, list question history, fetch an article, or ask a new question (with optional follow-up thread). Use when the user asks medical / evidence-based clinical questions, references…
wtfp-research-literature
This skill researches, organizes, and audits scholarly literature for an academic manuscript. It activates when an agent needs to investigate a research gap, analyze a bibliography, map references to sections, validate citation coverage, repair reference metadata, or perform the WTF-P research-gap, analyze-bib, or…
pi-autoresearch-loop
Skill "pi-autoresearch-loop" from twaldin/flt, covering pi-autoresearch — autonomous experiment loop, installation, quick start, core concepts and two-file persistence model.
paper-retriever
Retrieve a scientific paper PDF given an arxiv URL, DOI, or paper title. Downloads to papers/ directory. Handles open-access retrieval (arxiv direct, Chrome print-to-pdf for publisher-direct HTML, Unpaywall, title-based open-repository search); for paywalled papers it hands off to whichever paper-retriever- access…
paper-process
Retrieve a paper, read it, and run the full per-paper propstore ingestion flow through nested skills. Give it a URL, DOI, or title.
extract-justifications
Extract intra-paper justification structure and author it through pks source propose-justification.