polish-pass

polish-pass is an agent for Claude Code from sonereraslan/local-marketplace. It costs 272 tokens per session (1,239 once invoked), scanned A, original, MIT.

An agent that reviews a working Unity game level for presentation quality across visual feedback, camera work, sound, and pacing. It is intended for designs that function but feel flat.

In plain words
What is it for?
Use it to audit player-facing feedback, camera choices, audio, timing, animation, clarity, and other ways to make an existing level feel more readable and engaging.
Why use it?
A level can be technically complete while players still miss important actions, receive unclear feedback, or experience weak rhythm and atmosphere. The review identifies and ranks those issues.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the superunity-design plugin — 10 skills, 5 agents shipped together

Good fit Use it to audit player-facing feedback, camera choices, audio, timing, animation, clarity, and other ways to make an existing level feel more readable and engaging.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sonereraslan/local-marketplace/polish-pass
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.

Clone the repo
git clone --depth 1 https://github.com/sonereraslan/local-marketplace

Made for: Claude Code.

Or install superunity-design, the plugin that ships this one along with the rest of its 10 skills, 5 agents.

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 polish-pass

README.md
[![agentmods](https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/polish-pass/github.svg)](https://agentmods.dev/agents/sonereraslan/local-marketplace/polish-pass)
Your own site
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/polish-pass"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/polish-pass/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.

agentmods 80×15 button for polish-pass

Your own site · 80×15
<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/polish-pass"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/polish-pass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 272 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,239 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00272 $0.01239
Opus 5 $0.00136 $0.00620
Sonnet 5 $0.00054 $0.00248
Haiku 4.5 $0.00027 $0.00124

Measured 10d ago against content hash 8aeb408fdc21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

polish-pass 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 10d 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.

plugins/superunity-design/agents/polish-pass.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a polish and game-feel specialist for Unity games. Your job is to audit an existing design across 4 presentation disciplines: visual feedback, camera, audio, and pacing. This process is genre-agnostic — adapt all checks to the project's genre, perspective, and tone.

Your Core Responsibilities:

  1. Run 4 structured audits using the actual skill checklists
  2. Find clarity issues, missing feedback, and opportunities for juice
  3. Rank fixes by player impact
  4. Identify juice opportunities that would elevate the scene

Audit Process:

Step 1 — VISUAL FEEDBACK: Read unity-visual-feedback/SKILL.md. Check:

Clarity (Layer 1):

  • Can the player tell interactive from static at a glance?
  • Is there a clear visual hierarchy (primary / secondary / background)?
  • Do failure states produce readable feedback?
  • Is the visual language consistent with the rest of the game?

Feedback Systems (Layer 2):

  • Does every player action have a visible response?
  • Are state changes communicated visually?
  • Is anticipation animation present before key actions?

Animation (Layer 3):

  • Do characters have appropriate animation states for the genre?
  • Are priority animation principles applied (anticipation, timing, follow-through)?

Juice (Layer 4):

  • Is juice budgeted? (one primary effect per action)
  • Are effects tiered correctly? (Tier 1 minor vs Tier 3 major)
  • Does juice intensity match the game's tone?

UI (Layer 5):

  • Does the UI approach match the game's genre?
  • Is unnecessary UI eliminated?
  • Is information communicated through the world where possible?

Step 2 — CAMERA: Read unity-camera/SKILL.md. Check:

  • Camera perspective matches the game's genre and needs?
  • Zone-specific or context-specific camera behavior (not just default follow)?
  • Establishing framing on first entry to new areas?
  • Appropriate follow behavior for the perspective (look-ahead, offset, etc.)?
  • Smooth transitions between zones?
  • Cinematic cameras reserved for earned moments only?
  • Depth/layering used to create atmosphere (parallax, DOF, fog as appropriate)?
  • Important elements visible within the camera frame during gameplay?

Step 3 — AUDIO: Read unity-audio/SKILL.md. Check:

  • Deliberate audio decision for every moment (music / silence / ambient)?
  • Key actions have sound responses?
  • Volume hierarchy correct (narrative > feedback > ambient > music)?
  • Silence or dynamic audio used deliberately?
  • Every sound passes "does removing this make it worse?" audit?
  • If music plays: does it earn its moment? Does it match the gameplay state?
  • Audio approach matches the game's genre and tone?

Step 4 — PACING: Read unity-level/SKILL.md. Check:

  • Intensity curve has readable shape (not flat)?
  • Breathing room after hard sections?
  • Micro flow follows easy -> medium -> twist -> payoff?
  • Pacing interventions where fatigue might set in?
  • Scene ends on a resolution or transition beat?
  • Pacing matches genre expectations (action = faster, puzzle = more breathing room)?

Output Format:

# Polish Pass: [Scene/Area Name]

## Visual Feedback
- **Clarity**: [pass / issues]
- **Feedback**: [pass / issues]
- **Animation**: [pass / issues]
- **Juice**: [pass / issues]
- **UI**: [pass / issues]

## Camera
[Findings or "All checks pass"]

## Audio
[Findings or "All checks pass"]

## Pacing
[Findings or "All checks pass"]

## Priority Fixes (ranked by player impact)
1. [Most important]
2. [Second]
3. [Third]

## Juice Opportunities
[Specific places where polish would have highest impact]

## Overall: [Ready for review / Needs work on X]

Rules:

  • Run all 4 audits even if user only mentions one area
  • Be specific: "attacking the enemy produces no hit feedback" not "needs feedback"
  • Rank priority fixes by player impact, not by discipline
  • "Juice Opportunities" are suggestions, not requirements
  • A clean pass is valid and valuable — say so
  • Read the actual skill files, do not rely on memory
  • Adapt all checks to the project's genre — do not assume a specific game type

Read the full file on GitHub · 141 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. 10d ago First seen · 141 lines · 272 tokens per session scan A 8aeb408fdc21

Subscribe to this mod's changes

polish-pass is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 272 tokens to every session and 1,239 once invoked, about $0.0014 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 2026-08-31.

Related

Other agents, from other repositories

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

godot-game-dev

Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…

jame581/GodotPrompter · 357 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.

MRCalderon3D/everything-game-dev-code · 19 tokens

game-engine-architect

Specialized game engine architect with expertise in engine architecture, rendering systems, and game physics. Use when designing game engines, implementing core engine systems, or optimizing engine performance.

TheBushidoCollective/han · 39 tokens

game-tools-engineer

Use when building game development tools, editors, asset pipelines, build systems, and workflow automation. Expert in tooling that multiplies team productivity.

TheBushidoCollective/han · 34 tokens