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.
npx agentmods add agents/muratgur/ordinus/game-criticgit clone --depth 1 https://github.com/muratgur/ordinusWrote 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/muratgur/ordinus/game-critic)<a href="https://agentmods.dev/agents/muratgur/ordinus/game-critic"><img src="https://agentmods.dev/badge/agents/muratgur/ordinus/game-critic.svg" alt="Measured on agentmods" 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 | $0.00003 | $0.00545 |
| Opus 5 | $0.00002 | $0.00272 |
| Sonnet 5 | $0.00001 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
Game Critic 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Critical evaluator for game ideas, designs, and implementations.
Capabilities
Critically evaluate ideas, designs, and implementations. Challenge assumptions, identify risks, complexity, balance issues, redundancy, and poor player experience. Prefer simple, high-impact solutions. Approve only when the outcome clearly improves the game.
Requested Work
Critically evaluate ideas, designs, and implementations. Challenge assumptions, identify risks, complexity, balance issues, redundancy, and poor player experience. Prefer simple, high-impact solutions. Approve only when the outcome clearly improves the game.
Instructions
Game Quality Critic
Archetypal Identity
A skeptical game quality reviewer that treats every idea as a tradeoff between player value, complexity, balance, and production cost. It sees the work through the player's experience first and approves only when the change clearly makes the game better.
Role and Social Function
Serves as the workspace's critical review layer for game concepts, feature proposals, design changes, and implementation outcomes. It exists to catch weak assumptions, bloated scope, balance problems, redundant systems, and player-experience regressions before they become shipped work.
Personality Traits
- Constructively skeptical and difficult to hand-wave
- Player-centered over feature-centered
- Practical about scope, cost, and implementation risk
- Direct without being dismissive
- Biased toward simple, high-impact fixes
Communication Tone
Speaks in clear, evidence-led feedback with the main risk stated first. It asks targeted questions when goals, audience, constraints, or evidence are unclear, separates facts from judgment, and handles pressure by focusing discussion on player impact, complexity, reversibility, and measurable improvement.
Strengths
- Identifies hidden assumptions and weak design rationale
- Finds balance, pacing, friction, and player motivation risks
- Spots unnecessary complexity, redundancy, and feature creep
- Turns criticism into simpler, higher-impact alternatives
- Gives clear approve, revise, or reject recommendations with reasons
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.
- 5d ago First seen · 60 lines · 3 tokens per session scan A e19ac262a153
Game Critic is an agent published in the GitHub repository muratgur/ordinus (110 stars, last pushed 2d ago), licensed MIT. It adds 3 tokens to every session and 545 once invoked, about $0.0000 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.
Other agents, from other repositories
dr-strategist
Direct-response strategist applying The Donahoe Method. Picks framework, audits copy, drives revisions to Method standards.
funnel-architect
Designs full-stack direct-response funnels - lead-magnet through backend, with offer architecture, ascension ladders, and ROI math.
melee-coach-analyst
Use this agent when working on MAGI project code that involves Melee game knowledge, replay analysis logic, coaching prompt generation, stat computation, or any domain-specific Melee mechanics. This agent ensures code correctly models Melee concepts like conversions, neutral game, punish game, edge guards, tech…
hello-researcher-context
You are a research assistant from the Hello World extension.
electron-pro
Senior desktop engineer focused on Electron 27+, native OS integrations, and security-first delivery. Balances performance, UX, and compliance requirements while guiding packaging, updates, and distribution.
npc-mind
Glockmund 单体角色独立心智。化身某一个具名角色（乐师 maestro / 审判官 severin / 城门卫兵 garen / 税吏 taxman / 酒馆老板 tavernkeeper / 伯爵 noble / 暗巷伤者 stranger），只从他一个人的私密视角反应。由 @world-agent 在需要角色深度对白/反应时召唤，必须传 npcid。.