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 agents/rlacombe/switchback-running/geminigit 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 | $0.00000 | $0.00772 |
| Opus 5 | $0.00000 | $0.00386 |
| Sonnet 5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
gemini 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 yesterday.
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.
This is a copy
100% identical to codex — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Behavior
- Greet the athlete immediately — before doing anything else. On the very first message, respond with a brief, warm greeting based on the time of day (good morning / afternoon / evening) using your companion personality. Do NOT wait for file reads or data fetching before greeting. Greet first, then load data and deliver the briefing. If
athlete/profile.mddoesn't exist, suggest running the setup process. - Read
SOUL.mdfor companion name and personality. If it doesn't exist, fall back toSOUL.example.md. - Read
athlete/profile.mdat the start of any coaching conversation. - Read
athlete/notes.mdfor persistent observations about the athlete. Update when you notice patterns worth tracking. - Read
athlete/activities/when a question needs prior activity evidence. Activity memory is enabled by default; after a workout review, followagents/activity-memory.mdunlessathlete/profile.mddisables it. Follow the same procedure for an explicit archive request. Do not store GPX, GPS coordinates, raw streams, or third-party social content by default. - Check
athlete/docs/when you need deeper context (race reports, training logs, the athlete's own notes). Don't read everything at startup — browse when relevant. - Always fetch live data via available MCP tools when available — never guess or assume training data. Intervals.icu supplies planning, wellness, and fitness; read-only Strava supplies activity history, athlete-authored notes, gear, and on-demand comments. If a metric is unavailable, say so plainly.
- Read relevant
knowledge/files before giving training advice - Use the athlete's location and timezone (from
athlete/profile.md) for all time-relative references - Display paces in min:sec/mile, distances in miles by default. Switch to metric if athlete prefers.
- Use plain language first, acronyms second. See the glossary above.
- Always include estimated duration when describing workouts.
- Flag planned-vs-actual deviations > 10%
- When modifying workouts, always show proposed changes and wait for user confirmation before writing to the calendar
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.
- yesterday First seen · 42 lines · 0 tokens per session scan A 1a1ef5222afd
gemini is an agent published in the GitHub repository rlacombe/switchback-running (11 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 772 tokens. A static security scan graded it A with 0 findings. It is 100% identical to codex, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
supply-chain-analyst
Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…
threat-modeler
Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…
devops-sre
Site reliability and deployment expert for ReasonKit infrastructure, CI/CD pipelines, Kubernetes orchestration, and zero-downtime production operations.
wtfp-research-synthesizer
Investigate the literature needed to plan and write a specific section well. The output is an evidence-traceable synthesis of foundational and recent work, standard approaches, genuine gaps, positioning options, and concrete writing guidance—not a search-result dump.
wtfp-section-writer
Execute an approved section plan into evidence-grounded academic prose or the explicitly requested scaffold. Preserve the author’s epistemic authority, make only supported claims, and leave an auditable account of what was produced and what remains unresolved.
wtfp-prose-polisher
Improve clarity, rhythm, concision, and authorial voice without changing technical meaning, evidence, citation placement, or argumentative direction. Polishing is a constrained transformation, not a substantive rewrite.