hevy-mcp: Instructions file for Codex

AGENTS.md

hevy-mcp AGENTS.md is an instructions file for Codex, OpenCode from gCuadros/hevy-mcp. It costs 4,744 tokens per session, scanned C, original, MIT.

Repository instructions for Hevy Coach MCP, a server that lets an AI assistant access a user’s Hevy workout log and receive calculated training statistics. MCP is a standard way for AI assistants to call tools.

In plain words
What is it for?
Use them when changing workout analytics such as estimated one-rep maxes, personal records, muscle-group volume, consistency, or time-period comparisons, and when validating the server.
Why use it?
They identify the project’s source of truth and prevent arithmetic from being moved into the assistant, where calculations could become unreliable.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is gCuadros/hevy-mcp's own configuration. It tells Codex and OpenCode how to work on hevy-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-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to gCuadros/hevy-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/gCuadros/hevy-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/gCuadros/hevy-mcp

Made for: Codex, OpenCode.

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-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/gcuadros/hevy-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/gcuadros/hevy-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,744 This file is loaded in full into every session.
When invoked 4,744 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.04744 $0.04744
Opus 5 $0.02372 $0.02372
Sonnet 5 $0.00949 $0.00949
Haiku 4.5 $0.00474 $0.00474

Measured 8d ago against content hash 31938c4178c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

hevy-mcp AGENTS.md scanned grade C 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

yarn build # rm -rf dist && tsc -p tsconfig.build.json
AGENTS.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working in this repository. This file is the single source of truth; CLAUDE.md and .github/copilot-instructions.md only point back here. Subdirectories with rules of their own carry a nested AGENTS.md — read it when you touch that directory.

What this project is

hevy-coach-mcp is an MCP server that gives an AI assistant access to a user's Hevy training log, and computes the analytics on top of it: estimated 1RM, PRs, volume per muscle group, consistency, period-over-period comparison.

The guiding principle, which explains most of the design: the server computes the numbers, the model makes the judgements. All arithmetic lives in src/engine/ as a pure library, tested against fixtures, with no I/O. The assistant never does maths on training data — it interprets results it was handed. If you find yourself moving a calculation into a tool description or expecting the model to add things up, you have broken the core contract.

Requires Hevy PRO, which is what unlocks Hevy's API.

Validate your changes

There is no linter and no formatter in this repo. yarn lint does not exist — do not run it. A change is validated when all three of these pass:

yarn typecheck   # tsc --noEmit
yarn test        # vitest run
yarn build       # rm -rf dist && tsc -p tsconfig.build.json

Run all three before you call any task finished. CI (.github/workflows/ci.yml) runs exactly the same three, then packs the tarball and asserts what is inside it: that dist/stdio.js is present and still has its shebang, and that no compiled test or dist/store/ came along. That step needs nothing from you locally — it guards a mistake that is invisible until someone opens the published package.

CI has a second job, changeset, which fails when a pull request adds no changeset. It is not a required check, because docs-only and chore branches have nothing to announce: add the changeset, or label the pull request no-changeset.

Read the full file on GitHub · 344 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. 8d ago First seen · 344 lines · 4,744 tokens per session scan C 31938c4178c8

Subscribe to this mod's changes

hevy-mcp AGENTS.md is an instructions file published in the GitHub repository gCuadros/hevy-mcp (1 stars, last pushed 8d ago), licensed MIT. It adds 4,744 tokens to every session, about $0.0237 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens