What is puregym-mcp AGENTS.md?

A set of instructions for working on the PureGym client library and MCP server. PureGym is a gym service whose classes and bookings can be accessed through the package, either anonymously or with account credentials.

Use it when modifying the PureGym client, service layer, data models, filters, MCP server, or related tools.

It gives coding agents the repository structure, operating modes, domain rules, and workflow constraints they need before changing code.

How JorgeSintes/puregym-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to JorgeSintes/puregym-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/JorgeSintes/puregym-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/JorgeSintes/puregym-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jorgesintes/puregym-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/jorgesintes/puregym-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/jorgesintes/puregym-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jorgesintes/puregym-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/jorgesintes/puregym-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jorgesintes/puregym-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 768 This file is loaded in full into every session.

When invoked 768 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.

Model	Per session	Once invoked
Fable 5.1	$0.00768	$0.00768
Opus 5.5	$0.00307	$0.00307
Sonnet 5.5	$0.00154	$0.00154
Haiku 4.5	$0.00077	$0.00077

Measured 2mo ago against content hash 0b4e0a769148, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

puregym-mcp AGENTS.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 2mo 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.

AGENTS.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Repo Overview

This repo contains the publishable PureGym client library and MCP server package.
It is designed to work in two modes:
- Anonymous read-only mode when credentials are absent.
- Authenticated self-hosted mode when PUREGYM_USERNAME and PUREGYM_PASSWORD are set.
The Telegram bot lives in a separate puregym-bot repo and depends on this package.

Main Architecture

puregym_mcp/puregym/client.py
- Low-level PureGym HTTP client and login/session handling.
- Supports anonymous mode when credentials are absent and authenticated mode when env credentials are present.
puregym_mcp/puregym/service.py
- Reusable service layer used by both MCP tools and the bot.
- Owns default search windows: 14 days anonymous, 28 days authenticated.
puregym_mcp/puregym/schemas.py
- Structured PureGym models.
- Includes derived fields like is_booked, is_waitlisted, waitlist_position, and waitlist_size.
puregym_mcp/puregym/filters.py
- Shared class filtering helpers used by consumers like the bot.
puregym_mcp/mcp/server.py
- MCP server bootstrap.
puregym_mcp/mcp/tools.py
- MCP tool registration.
- Always exposes read-only tools; exposes mutation tools only in authenticated mode.
puregym_mcp/mcp/capabilities.py
- Declares which tool capabilities are available in the current mode.

Important Domain Rules

Keep this repo focused on structured PureGym domain logic and MCP exposure.
Do not add Telegram formatting or bot-specific interaction logic here.
puregym-mcp has two intended modes:
- Anonymous/read-only mode for hosted or public use.
- Authenticated mode for self-hosted use via PUREGYM_USERNAME and PUREGYM_PASSWORD env vars.
Do not design for hosted authenticated MCP. That is intentionally out of scope.
MCP tool outputs should stay structured and derived, not chat-formatted.

Workflow Rules For Future Changes

Always use uv for project commands.
Prefer:
- uv sync --dev
- uv run pytest
- uv run python -m compileall puregym_mcp tests
- uv run puregym-mcp
- uv add ... / uv sync when dependency changes are needed
Do not use plain python, pip, or ad-hoc environment commands when uv can do the job.

Read the full file on GitHub · 73 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.

2mo ago First seen · 73 lines · 768 tokens per session scan A 0b4e0a769148

Subscribe to this mod's changes

puregym-mcp AGENTS.md is an instructions file published in the GitHub repository JorgeSintes/puregym-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 768 tokens to every session, about $0.0031 per session on Opus 5.5. 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.

puregym-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
puregym-mcp AGENTS.mdJorgeSintes/puregym-mcp	Instructions file	2	6mo ago	MIT	A	768	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

puregym-mcp: Instructions file for Codex