Borrowing it
Nothing to install: this file belongs to atomchung/long-run-hybrid-coach. 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/atomchung/long-run-hybrid-coach/main/CLAUDE.mdgit clone --depth 1 https://github.com/atomchung/long-run-hybrid-coachWrote 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/atomchung/long-run-hybrid-coach/claude-md)<a href="https://agentmods.dev/instructions/atomchung/long-run-hybrid-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/atomchung/long-run-hybrid-coach/claude-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/atomchung/long-run-hybrid-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/atomchung/long-run-hybrid-coach/claude-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 | $0.01941 | $0.01941 |
| Opus 5 | $0.00971 | $0.00971 |
| Sonnet 5 | $0.00388 | $0.00388 |
| Haiku 4.5 | $0.00194 | $0.00194 |
Grade A, and why
long-run-hybrid-coach CLAUDE.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 5d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working rules for Claude
Repository invariants and the verification commands are in AGENTS.md. The product surface, state mechanics, and delivery boundary are in README.md. Both apply to Claude unchanged. They are not restated here: a second copy is a second source of truth, and it drifts.
This file covers only what those two do not — how to work in this repository from one session to the next.
A bare issue #NN inside code is history, not a live link
Most of this code was written in a private repository that is now archived, and its comments cite that repository's numbers. Those numbers do not resolve here, and a few collide with real issues in this one. Read them as provenance for work already done — never follow one, and never cite one in new code. Anything still open was refiled here and is listed in the migration tracker, issue #37.
Start from stored state, never from conversation memory
Before deciding anything about the plan:
python3 -m garmin_coach_loop.cli doctor-store
python3 -m garmin_coach_loop.cli status
A plan reconstructed from what an earlier conversation said is a second plan. The store holds the only current one, and reading it is cheap.
Once this machine names a hosted coach (GARMIN_COACH_LOOP_GATEWAY_URL), the
canonical plan is the hosted one and the local store is history. Read it the way
every other client does:
python3 -m garmin_coach_loop.cli hosted-session
doctor-store/status still answer for whatever local store is being worked on;
they just stop being the answer to "what is the athlete's current plan".
Dogfooding runs on main, and writes in one place
The real store lives at ~/.local/share/garmin-coach-loop. A git worktree
isolates code, not state — so a work-in-progress branch pointed at the
default store writes real state from unreviewed code.
- Dogfood from the main checkout, on
main. - Develop in a worktree.
- Anything needing its own state sets
GARMIN_COACH_LOOP_HOME. - One writer per athlete. ChatGPT, claude.ai, a local MCP client and the CLI
all reach one hosted owner store; a writable local store beside it is a second
current plan for one Intervals calendar, which is what issue #40 is about. With
a hosted coach configured, local writes refuse unless
--offlinesays a different store is meant, and a migrated store is sealed (hosted-handoff.json) so no code path writes it at all. Moving an existing local store across once: docs/ops/migrate-local-store-to-hosted.md. - Every refresh passes
--health-db, or exportsGARMIN_COACH_LOOP_HEALTH_DBonce:
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.
- 5d ago Changed · +6 lines · +99 tokens per session f7abdf01877e
- 10d ago First seen · 147 lines · 1,842 tokens per session scan A 35431d895b0d
long-run-hybrid-coach CLAUDE.md is an instructions file published in the GitHub repository atomchung/long-run-hybrid-coach (4 stars, last pushed yesterday), licensed MIT. It adds 1,941 tokens to every session, about $0.0097 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 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.