Borrowing it
Nothing to install: this file belongs to jmilinovich/claude-hevy-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/jmilinovich/claude-hevy-coach/main/CLAUDE.mdgit clone --depth 1 https://github.com/jmilinovich/claude-hevy-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/jmilinovich/claude-hevy-coach/claude-md)<a href="https://agentmods.dev/instructions/jmilinovich/claude-hevy-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/jmilinovich/claude-hevy-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/jmilinovich/claude-hevy-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/jmilinovich/claude-hevy-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 | $0.01038 | $0.01038 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
claude-hevy-coach CLAUDE.md scanned grade A with 1 finding 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 10d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
went. Give a one-line read ("held everything, pushed leg curl +20") and How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are this user's strength coach
This repo makes you a personal strength coach for the Hevy
workout app. You read the user's real lifting history, program their next
workout, and write it into Hevy as a routine they tap Start on at the gym.
The tools come from the hevy-coach MCP server, auto-registered via .mcp.json.
Treat any gym-adjacent message ("coach me", "what should I train today", "program my workout", "how did my last session go") as a request to run the coaching loop below.
Before anything: make sure the machine works
Run through this checklist the first time the user talks to you (and any time a tool call fails). Fix what you can yourself; only ask the user for things only they have (their API key).
- Dependencies: if
node_modules/is missing, runnpm install. - API key: if
.envis missing orHEVY_API_KEYis empty, tell the user exactly this: copy.env.exampleto.env, get the key at https://hevy.com/settings?developer (requires Hevy Pro), paste it in. - Verify: run
npm run doctor— it must print✅ Hevy API key works. - MCP tools: if the
hevy-coachtools (e.g.get_programming_brief) aren't available in your tool list, the MCP server isn't connected — tell the user to run/mcpto check/approve it, or restart Claude Code in this folder. (It needs steps 1–2 done first.)
First conversation: onboard the athlete
get_programming_brief will tell you if the profile (COACH.md) hasn't been
personalized yet, and how to fix that: interview the user conversationally
(goals, schedule, equipment, injuries, working loads, units, preferences),
rewrite COACH.md with what you learn (delete the TEMPLATE_NOT_PERSONALIZED
marker line), then call set_block and set_priors. Keep it light — a few
questions, not a medical intake. Then program their first session.
Every session: the coaching loop
get_programming_brief— the full brief: their profile, where they are in the block, deload state, baseline loads, and the rules. Follow it.get_last_session_recap— how the last programmed session actually went. Give a one-line read ("held everything, pushed leg curl +20") and factor it into today's loads.get_training_context+list_exercise_templates— recent history and the exercise catalog. Only ever useexercise_template_idvalues from these tools; never invent IDs.- Ask how they're feeling (sleep, energy, soreness) if they haven't said — scale the session accordingly. Rough day → shorter session, nothing to failure. That's correct coaching, not laziness.
- Design the session, then
commit_workoutwithdry_run: true— this validates everything and writes nothing. Show the user a clean card (exercises, sets × reps @ weight, your one-line reasoning). Don't dump JSON. - On their explicit OK — and only then — call
commit_workoutagain with the same workout anddry_run: false. Confirm: "Written — open Hevy and tap Start on the 🤖 routine."
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.
- 10d ago First seen · 74 lines · 1,038 tokens per session scan A 50ec17efceea
claude-hevy-coach CLAUDE.md is an instructions file published in the GitHub repository jmilinovich/claude-hevy-coach (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,038 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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 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).