game-playtest

game-playtest is a skill for Claude Code, Codex from AlterLab-IEU/AlterLab_GameForge. It costs 97 tokens per session (5,488 once invoked), scanned A, original, MIT.

A structured method for watching players use a game and turning their behavior into design feedback. It covers session plans, observation guides, and analysis.

In plain words
What is it for?
Planning playtests, checking onboarding and difficulty, evaluating new features, and summarizing player behavior into design changes.
Why use it?
It replaces vague opinions such as “the game is fun” with evidence about what players understand, miss, or struggle with.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/alterlab-ieu/alterlab_gameforge/game-playtest
Any agent
npx skills add AlterLab-IEU/AlterLab_GameForge --skill game-playtest
Clone the repo
git clone --depth 1 https://github.com/AlterLab-IEU/AlterLab_GameForge

Made for: Claude Code, 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.

agentmods badge for game-playtest

README.md
[![agentmods](https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-playtest.svg)](https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-playtest)
Your own site
<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-playtest"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-playtest.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,488 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00097 $0.05488
Opus 5 $0.00048 $0.02744
Sonnet 5 $0.00019 $0.01098
Haiku 4.5 $0.00010 $0.00549

Measured 5d ago against content hash b76d7c107c5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

game-playtest 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 5d 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.

skills/workflows/game-playtest/SKILL.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AlterLab GameForge -- Structured Playtest Analysis

Playtesting is not asking players if they had fun. It is the disciplined observation of player behavior to identify where the design succeeds and where it fails. The player's mouth lies -- their hands do not. Nintendo has known this for decades: Miyamoto famously watches players silently, trusting their confusion over their compliments. Larian ran thousands of community playtests during BG3's Early Access, and every major system change traced back to behavioral data, not forum polls. This workflow provides a rigorous behavioral observation framework that transforms raw playtest sessions into actionable design insights.

Purpose & Triggers

Invoke this workflow when:

  • A build is ready for external eyes and you need structured feedback, not just reactions
  • Specific design questions need answering: "Do players understand the crafting system?" not "Is the game good?"
  • Onboarding flow needs validation -- can new players learn the core mechanic without a tutorial?
  • Difficulty curve assessment -- are players in the flow channel or oscillating between boredom and frustration?
  • A new feature has been integrated and its impact on the overall experience is unknown
  • Pre-release polish pass needs data on which rough edges matter most to players
  • Competitive analysis requires side-by-side comparison with a reference game

Do NOT use this workflow when:

  • You need to test a raw mechanic in isolation (use game-prototype instead)
  • The build is so broken that testers will spend most of their time hitting bugs (fix critical bugs first, then playtest)
  • You want marketing quotes or positive testimonials (that is PR, not playtesting)

Critical Rules

  1. Define questions before inviting testers. Every playtest answers specific questions. "Is it fun?" is not a question -- it is a prayer. "Can players complete the first dungeon without dying more than twice?" is a question. Celeste's playtests asked "can players learn the dash mechanic within the first three screens?" -- specific, observable, actionable.
  2. The facilitator does not play. You observe. You take notes. You do not help, explain, suggest, or react. Your poker face is a scientific instrument.
  3. Minimum 5 testers per session. Fewer than 5 and you are collecting anecdotes, not data. Individual player quirks dominate small samples. At 5+ testers, patterns emerge.
  4. Never test with the development team. They know too much. Their muscle memory, mental models, and context make them incapable of experiencing the game as a new player. Nintendo's internal playtesting teams are deliberately kept away from development discussions so they approach each session cold. Your developers are blind to every onboarding problem they have already internalized.
  5. Behavioral data outranks verbal data. If a player says "the controls feel fine" but you observed them pressing the wrong button 11 times in a 10-minute session, the behavioral data wins. Always. Larian tracked BG3 playtester behavior at the input level -- they knew which dialogue options players hovered over before choosing, and that hesitation data informed their rewrite of Act 1.
  6. Separate observation from interpretation. During the session, record what happened. After the session, interpret what it means. Mixing the two in real-time creates confirmation bias.
  7. Reference docs/game-design-theory.md for Flow Theory and MDA Framework when analyzing player engagement and emotional responses.

Read the full file on GitHub · 379 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. 5d ago First seen · 379 lines · 97 tokens per session scan A b76d7c107c5a

Subscribe to this mod's changes

game-playtest is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (34 stars, last pushed 5mo ago), licensed MIT. It adds 97 tokens to every session and 5,488 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

pufferlib

Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.

K-Dense-AI/scientific-agent-skills · 65 tokens

build-world

Builds polished, fully playable 3D game prototypes in Unity, Roblox, or three.js with high-quality (.glb) meshes from the Thrixel API, and publishes finished games to a public thrixel.world link that anyone can play in a browser. Use when the user wants to make a game, build a playable prototype, or generate 3D assets…

thrixel/build-world · 120 tokens

meshy-3d-generation

Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…

meshy-dev/meshy-3d-agent · 101 tokens

meshy-openclaw

Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture…

meshy-dev/meshy-3d-agent · 128 tokens

2dimg2motion

Use when a user provides one baseline image and requests game animation frames, sprite sequences, attack/walk/idle/hit/death/casting motion, transparent PNG frames, a spritesheet, keyframe prompts, or consistent whole-character pose animation.

WU-HAOTIAN34/2dimg2motion · 55 tokens

img2mo-learn

Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…

WU-HAOTIAN34/2dimg2motion · 104 tokens