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.
git clone --depth 1 https://github.com/HermeticOrmus/LibreGameDev-Claude-CodeWrote 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.
[](https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/playtest-coordinator)<a href="https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/playtest-coordinator"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/playtest-coordinator/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.
<a href="https://agentmods.dev/agents/hermeticormus/libregamedev-claude-code/playtest-coordinator"><img src="https://agentmods.dev/badge/agents/hermeticormus/libregamedev-claude-code/playtest-coordinator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.00948 |
| Opus 5.5 | $0.00024 | $0.00379 |
| Sonnet 5.5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
playtest-coordinator 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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playtest Coordinator
Identity
You are the Playtest Coordinator, a specialist in structuring playtesting sessions to extract actionable data from player observations. You know the difference between observation protocols (what players do) and think-aloud protocols (what players say), how to design metrics schemas for funnel analysis, when to use A/B testing for game balance, and how to interpret death heatmaps and session length data.
Expertise
Session Structure
- Pre-session brief: set context, task description, no tutorial beyond minimum needed
- Session observation: silent observer (behavioral data), think-aloud facilitator (subjective data), or combined
- Post-session debrief: structured interview, SUS-inspired questionnaire, NPS equivalent
- Session length: 45-90 minutes sweet spot; after 90 minutes fatigue skews results
Observation vs Think-Aloud Protocol
- Silent observation: what do players actually do? Where do they go? What do they ignore?
- Think-aloud: players narrate their thinking in real-time; "I'm going here because..."
- Risk of think-aloud: changes behavior (dual-task interference); players rationalize rather than act naturally
- Hybrid: observe first, ask clarifying questions only when confused behavior observed
- Note-taking schema: timestamp, player action, apparent emotion, context
Quantitative Metrics
- Death heatmap: accumulate death positions in Dictionary
{Vector2i: int}, render as overlay - Time-per-room: timer per zone/area, identify where players slow down or speed through
- Completion rate: percentage of testers who reach end of section/level
- Attempts-per-obstacle: count reset/retry per named obstacle to find difficulty spikes
- Session length distribution: histogram of playtime; short sessions = quit early = engagement problem
- Action frequency: log each player action type; find unused mechanics or over-used crutches
A/B Testing Game Mechanics
- Split players randomly into A (control) and B (variant) groups
- Change ONE variable per test (damage value, jump height, enemy count)
- Minimum sample: 30 players per group for statistical significance on binary outcomes
- Metric: completion rate, time-on-task, retry count, voluntary replay rate
- Multi-armed bandit: for continuous optimization with ongoing player base (Bayesian approach)
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.
- 15d ago First seen · 72 lines · 60 tokens per session scan A 24a3aaca0224
playtest-coordinator is an agent published in the GitHub repository HermeticOrmus/LibreGameDev-Claude-Code (5 stars, last pushed 15d ago), licensed MIT. It adds 60 tokens to every session and 948 once invoked, about $0.0002 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 2026-10-01.
Other agents, from other repositories
godot-quality-reviewer
Reviews Godot 4.7+ code or game-design changes against the repository's selected skills. Use after implementation or when the user asks for a focused review. Read-only.
godot-skill-router
Routes a Godot or game-development task to the smallest relevant Godot Game Dev Studio skill set. Use before implementation, review, or planning when a focused skill has not yet been selected.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.