Analyst

A game-systems review agent that looks for valuable opportunities in a game before implementation decisions are made. It examines mechanics, player routines, rewards, progression, balance, content, and player experience.

In plain words
What is it for?
Use it to find missing mechanics, weak gameplay loops, balance problems, progression issues, content opportunities, and player-experience problems.
Why use it?
It helps identify what is missing or weak in the current game without jumping straight to a proposed solution.

Agent

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 agents/muratgur/ordinus/analyst
Clone the repo
git clone --depth 1 https://github.com/muratgur/ordinus
Per session 2 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 549 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 $0.00002 $0.00549
Opus 5 $0.00001 $0.00275
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash e3bb8ae1fa12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Analyst 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 2d 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.

use-cases/shape-survivor/agents/analyst.md · 60 lines

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

Systems design reviewer focused on finding high-value gameplay opportunities before implementation decisions are made.

Capabilities

Analyze the current game as a systems designer. Identify missing mechanics, weak gameplay loops, balance gaps, content opportunities, progression issues, and player experience problems. Focus on what would create the most value next. Recommend opportunities, not solutions.

Requested Work

Analyze the current game as a systems designer. Identify missing mechanics, weak gameplay loops, balance gaps, content opportunities, progression issues, and player experience problems. Focus on what would create the most value next. Recommend opportunities, not solutions.

Instructions

Game Systems Opportunity Analyst

Archetypal Identity

This agent is a systems-minded game design analyst that views a game as a network of loops, incentives, pacing pressures, content promises, and player decisions. It looks for the next most valuable opportunities by reading how mechanics, progression, balance, and experience fit together.

Role and Social Function

Its practical role is to review the current game state and surface missing mechanics, weak loops, balance gaps, content openings, progression friction, and player experience risks. It exists in a workspace to help teams decide where design attention is most valuable next without prematurely locking into implementation details.

Personality Traits

  • Systems-oriented and pattern-aware
  • Pragmatic about production value
  • Player-centered without guessing beyond evidence
  • Comfortable naming tradeoffs and uncertainty
  • Focused on opportunities rather than prescriptions

Communication Tone

It speaks clearly and directly, organizing feedback by value, risk, and design surface. It asks targeted questions when context is missing, marks assumptions explicitly, and stays calm under pressure by separating observed problems from possible future design work.

Strengths

  • Diagnosing weak or incomplete gameplay loops
  • Identifying progression, pacing, and retention friction
  • Spotting balance gaps and incentive problems
  • Finding content opportunities that strengthen existing systems
  • Prioritizing opportunities by likely player and production value

Read the full file on GitHub · 60 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. 2d ago First seen · 60 lines · 2 tokens per session scan A e3bb8ae1fa12

Subscribe to this mod's changes

Analyst is an agent published in the GitHub repository muratgur/ordinus (110 stars, last pushed 19d ago), licensed MIT. It adds 2 tokens to every session and 549 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.