A toolkit and workflow for creating and testing Ren'Py visual novels, which are story-driven games with images, dialogue, and choices. It supports project editing, builds, previews, generated artwork, and browser playtesting.

Use it to start or modify a Ren'Py game, create narrative and visual content, build or preview it, and test supported screens in a browser.

It gives a visual-novel project a documented starting structure and separates story, art, build, and testing work. Existing projects can be edited without replacing their structure.

renpy — Skill for Codex by banjtheman/renpy_mcp

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add banjtheman/renpy_mcp_server --skill renpy

Clone the repo

git clone --depth 1 https://github.com/banjtheman/renpy_mcp_server

Made for: Codex.

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/skills/banjtheman/renpy_mcp_server/renpy/github.svg)](https://agentmods.dev/skills/banjtheman/renpy_mcp_server/renpy)

Your own site

<a href="https://agentmods.dev/skills/banjtheman/renpy_mcp_server/renpy"><img src="https://agentmods.dev/badge/skills/banjtheman/renpy_mcp_server/renpy/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/skills/banjtheman/renpy_mcp_server/renpy"><img src="https://agentmods.dev/badge/skills/banjtheman/renpy_mcp_server/renpy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 744 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00023	$0.00744
Opus 5.5	$0.00009	$0.00298
Sonnet 5	$0.00005	$0.00149
Haiku 4.5	$0.00002	$0.00074

Measured 3d ago against content hash fa2f5c2854e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-25, from the pricing page.

Security

Grade A, and why

renpy 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 3d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (assets/web/renpy-agent.js, scripts/renpy.py, tests/test_bridge_python.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/renpy/SKILL.md · 43 lines

How it starts

The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ren'Py

Author Ren'Py projects directly in the user's workspace. This folder contains the project template, SDK/build/preview helper, and browser bridge. Resolve bundled paths relative to this SKILL.md; the folder can be copied to another skill installation without its containing repository.

Start from the task

New game or narrative/art work: read story-and-art.md. Shape the story and visuals around the user's brief. The starter is a runnable sample; replace its cast, plot, notes, and route tests as needed.
Existing game: preserve its structure and edit .rpy source directly. Use only the references relevant to the change; init is for a new project.
SDK, builds, or preview: read toolchain.md for prerequisites, configuration, and build behavior.
Browser playtesting or bridge integration: read browser-control.md for tool discovery, state, and supported screens.

For generated art, use the native ImageGen tool and the system imagegen skill that documents it. This workflow does not pin an image API model. If multiple imagegen skills are installed, select the one for the native tool. Selected files belong in the project, with their source references retained. If native generation is unavailable, report the limitation and continue with existing or temporary art where useful; an alternative image provider needs the user's choice.

Local toolchain

Use an available Python 3.11.8+ interpreter for scripts/renpy.py; it uses only the standard library. Ren'Py runs through the SDK's bundled runtime. Below, PYTHON and SKILL stand for the resolved absolute interpreter and skill-directory paths, not literal commands.

PYTHON SKILL/scripts/renpy.py setup
PYTHON SKILL/scripts/renpy.py doctor
PYTHON SKILL/scripts/renpy.py init /absolute/path/my-game --title "My Game"
PYTHON SKILL/scripts/renpy.py lint /absolute/path/my-game
PYTHON SKILL/scripts/renpy.py build-web /absolute/path/my-game
PYTHON SKILL/scripts/renpy.py serve /absolute/path/my-game
PYTHON SKILL/scripts/renpy.py status /absolute/path/my-game
PYTHON SKILL/scripts/renpy.py stop /absolute/path/my-game

Read the full file on GitHub · 43 lines

Files

What ships with it

17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 43 lines · 23 tokens per session scan A fa2f5c2854e4

Subscribe to this mod's changes

renpy is a skill published in the GitHub repository banjtheman/renpy_mcp_server (61 stars, last pushed 4d ago), licensed MIT. It adds 23 tokens to every session and 744 once invoked, about $0.0001 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 2026-09-22.

Creative and media Game development

renpy

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Ren'Py

Start from the task

Local toolchain

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

playtest-report

gameobject-component-destroy

unity-version-split

motion

unity-addressables

threejs-exposure-color-grading