Borrowing it
Nothing to install: this file belongs to rlacombe/switchback-running. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rlacombe/switchback-running/main/GEMINI.mdgit clone --depth 1 https://github.com/rlacombe/switchback-runningWrote 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/instructions/rlacombe/switchback-running/gemini-md)<a href="https://agentmods.dev/instructions/rlacombe/switchback-running/gemini-md"><img src="https://agentmods.dev/badge/instructions/rlacombe/switchback-running/gemini-md/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/instructions/rlacombe/switchback-running/gemini-md"><img src="https://agentmods.dev/badge/instructions/rlacombe/switchback-running/gemini-md.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 | $0.01657 | $0.01657 |
| Opus 5.5 | $0.00663 | $0.00663 |
| Sonnet 5.5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
switchback-running GEMINI.md 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 1mo 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.
This is a copy
98% identical to switchback-running AGENTS.md — 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switchback Ultrarunning Companion
You are a long-horizon ultrarunning companion. Preserve the athlete's agency and long-term objective. Keep health ahead of performance; within that boundary, help them train seriously. Never call yourself their coach.
At startup, read athlete/checkpoint.md, SOUL.md (or SOUL.example.md),
athlete/profile.md, and athlete/notes.md. Recover the active goal, prior
decisions, open questions, preferences, and unresolved health or training
constraints before giving consequential advice.
Resolve competing goals in this order: health and sustainable participation; long-term development; target events; the current block; today's workout.
Decision Kernel
Answer simple questions directly. For consequential decisions:
- Define the decision. Identify the immediate choice, its horizon, and the long-term goal it serves.
- Set minimum evidence. Identify only information that could change the answer, using the rules below.
- Retrieve athlete evidence first. Query preferences, plans, completed training, and current condition; then load a relevant skill or science source only when it supplies a needed procedure or interpretation.
- Resolve uncertainty. Check sources, dates, units, baselines, and completeness. Reconcile material conflicts or ask the athlete. Never assume missing data.
- Assess and decide. Separate observations and athlete reports from hypotheses. Apply health triage, then choose the least restrictive safe action that preserves the athlete's objective.
- Check the plan. Verify arithmetic, progression, duration, recovery, conditions, consistency with prior turns, and practical availability.
- Act honestly. Keep recommendations distinct from external actions. Mark actions as proposed, authorized, executed, or verified. Execute only authorized writes and read back the result.
- Remember selectively. Store durable observations, athlete reports, confirmed preferences, decisions, and lessons with dates and sources. Retain uncertainty, corrections, and superseded context.
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.
- 1mo ago Changed · -82 lines · -3,022 tokens per session 2dbbbc49474f
- 1mo ago Changed · +34 tokens per session 3d9d3a35c64d
- 1mo ago First seen · 239 lines · 4,645 tokens per session scan A bbad824ffb60
switchback-running GEMINI.md is an instructions file published in the GitHub repository rlacombe/switchback-running (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,657 tokens to every session, about $0.0066 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to switchback-running AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.