hevy-fitness-mcp: Instructions file for Claude Code

CLAUDE.md

hevy-fitness-mcp CLAUDE.md is an instructions file for Claude Code from ikeike443/hevy-fitness-mcp. It costs 663 tokens per session, scanned A, original, MIT.

Claude Code instructions for the hevy-fitness-mcp project. They describe the project workflow and safety rules for tools that write workout data.

In plain words
What is it for?
Planning repository changes through feature branches and pull requests, reviewing those pull requests, and following safety procedures for Hevy write operations.
Why use it?
They help keep changes reviewable by using pull requests and add checks around operations that can modify Hevy routines or other workout data.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; mentions AGENTS.md.

This is ikeike443/hevy-fitness-mcp's own configuration. It tells Claude Code how to work on hevy-fitness-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything hevy-fitness-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ikeike443/hevy-fitness-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ikeike443/hevy-fitness-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ikeike443/hevy-fitness-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for hevy-fitness-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ikeike443/hevy-fitness-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ikeike443/hevy-fitness-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ikeike443/hevy-fitness-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ikeike443/hevy-fitness-mcp/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.

agentmods 80×15 button for hevy-fitness-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ikeike443/hevy-fitness-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ikeike443/hevy-fitness-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 663 This file is loaded in full into every session.
When invoked 663 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00663 $0.00663
Opus 5 $0.00331 $0.00331
Sonnet 5 $0.00133 $0.00133
Haiku 4.5 $0.00066 $0.00066

Measured 11d ago against content hash 1dac7f2d962b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

hevy-fitness-mcp 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 11d 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.

CLAUDE.md · 23 lines

How it starts

The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@AGENTS.md

Workflow

Propose changes via pull request (feature branch + PR), not by committing directly to main. Open the PR and let the user review/merge, unless they explicitly ask for a direct push.

Every time you open a PR in this repo, automatically follow up with a two-step subagent loop — don't wait to be asked:

  1. Spawn a subagent to review the PR (diff + CI) and post its findings as a GitHub PR review, findings first, no inline fixing.
  2. Only if that review turns up findings, spawn a second, separate subagent to address them and push the fixes to the same branch. If the review finds nothing, stop after step 1 — no fix subagent needed.

This loop is the default when nothing else is specified. If the user gives explicit instructions about a specific self-opened PR — e.g. "just review this one, don't fix it yet", "hold off on fixing", or any other specific ask — those instructions win for that PR, overriding the automatic loop (including its automatic fix-and-push step), even though the assistant opened the PR itself.

When asked to review a PR that already existed before the current turn/request (e.g. reviewing someone else's PR, or a plain "review PR #N" request for a PR opened in an earlier session or task — as opposed to one the assistant is opening as part of the current task), post the review with findings first, as a separate step from fixing them. Don't fix-then-report in the same motion — it reads as unclear/backwards about what's already done vs. still open. Wait for the user (or a follow-up instruction) before pushing fixes for what the review found.

Hevy write-tool safety

This server's create_*/update_* MCP tools (create_routine, update_routine, create_routine_folder, create_workout, update_workout, create_custom_exercise_template, create_body_measurement, update_body_measurement) are real writes to whatever Hevy account HEVY_API_KEY points at, with no delete endpoint anywhere in Hevy's API to undo one automatically. This applies whenever this session calls those tools directly against a real account — most likely while doing the README's "Manually verifying Hevy write operations" checklist after a change to lib/hevy.ts or app/api/mcp/route.ts.

Read the full file on GitHub · 23 lines

Changes

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.

  1. 11d ago First seen · 23 lines · 663 tokens per session scan A 1dac7f2d962b

Subscribe to this mod's changes

hevy-fitness-mcp CLAUDE.md is an instructions file published in the GitHub repository ikeike443/hevy-fitness-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 663 tokens to every session, about $0.0033 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,126 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens