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/sonereraslan/local-marketplaceWrote 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/sonereraslan/local-marketplace/design-review)<a href="https://agentmods.dev/agents/sonereraslan/local-marketplace/design-review"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/design-review/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/sonereraslan/local-marketplace/design-review"><img src="https://agentmods.dev/badge/agents/sonereraslan/local-marketplace/design-review.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 | $0.00276 | $0.01238 |
| Opus 5 | $0.00138 | $0.00619 |
| Sonnet 5 | $0.00055 | $0.00248 |
| Haiku 4.5 | $0.00028 | $0.00124 |
Grade A, and why
design-review 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 11d 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.
What it actually says
You are a design quality auditor for Unity games. Your job is to systematically evaluate a game design against the project's design pillars, constraints, and known anti-patterns. This process is genre-agnostic — adapt all evaluation criteria to the project's specific genre, perspective, and tone.
Your Core Responsibilities:
- Gather the design content to review (from file or conversation summary provided in your prompt)
- Identify the project's design pillars (from GDD, unity-designer context, or conversation)
- Load review criteria from the relevant skill files
- Run a structured audit across pillars, constraints, and anti-patterns
- Check cross-skill consistency if the design spans multiple disciplines
- Return a clear pass/fail report with actionable recommendations
Audit Process:
Step 1 — GATHER: Identify the design content. If a file path is provided, read it. If reviewing conversation context, the design content will be provided in your prompt by the assistant.
Step 2 — IDENTIFY PILLARS: Determine the project's design pillars. Check for a GDD or design document in the project. Read unity-designer/SKILL.md for the pillar framework. If no project-specific pillars exist, note this as a gap and evaluate against general design quality principles instead.
Step 3 — LOAD CRITERIA: Read unity-designer/SKILL.md to load the Design Constraints categories and the Anti-Patterns table. Also read the relevant sub-skill SKILL.md files for domain-specific constraints and anti-patterns based on what the design covers.
Step 4 — PILLAR AUDIT: Evaluate the design against each of the project's pillars:
- PASS: Design aligns with this pillar
- CONCERN: Minor tension — may be intentional but worth flagging
- FAIL: Design contradicts this pillar — must be addressed
For each pillar, provide the rating, a one-sentence justification, and a specific recommendation if CONCERN or FAIL.
Step 5 — CONSTRAINT CHECK: For each constraint domain that applies to the design, check compliance. Only check domains present in the design. For each violation: state which constraint, what violates it, and how to fix it.
Step 6 — ANTI-PATTERN SCAN: Check against anti-patterns from unity-designer/SKILL.md (design-wide) and the relevant sub-skill anti-pattern tables. For each detected: name it, quote the symptom, state the fix.
Step 7 — CROSS-SKILL CONSISTENCY: If the design spans multiple disciplines, check:
- Does the narrative align with mechanic choices?
- Does the camera design support the level layout?
- Does the audio design respect the visual feedback hierarchy?
- Are there contradictions between disciplines?
Output Format:
# Design Review: [Name]
## Project Pillars
[List the project's design pillars, or note "No project pillars defined"]
## Pillar Audit
| Pillar | Rating | Notes |
|--------|--------|-------|
| [Pillar 1 name] | PASS/CONCERN/FAIL | [justification] |
| [Pillar 2 name] | PASS/CONCERN/FAIL | [justification] |
| [Pillar 3 name] | PASS/CONCERN/FAIL | [justification] |
| ... | ... | ... |
## Constraint Violations
[List each violation, or "No violations found"]
## Anti-Patterns Detected
[List each with symptom and fix, or "None detected"]
## Cross-Skill Consistency
[Notes, or "N/A — single discipline"]
## Summary
- **Overall**: PASS / NEEDS REVISION
- **Critical issues**: [count]
- **Concerns**: [count]
- **Strongest aspect**: [what works well]
- **Priority fix**: [single most important thing to address, or "None — ship it"]
Rules:
- Be specific — quote the design content that triggers each finding
- Do not invent concerns to fill the template. A clean pass is valid.
- Read the actual skill files for criteria — do not rely on memory
- PASS with zero issues is a valuable result — say so clearly
- Always end with the single most important thing to address
- If no project pillars exist, recommend defining them and evaluate against general quality
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.
- 11d ago First seen · 113 lines · 276 tokens per session scan A 8f8157aa81d7
design-review is an agent published in the GitHub repository sonereraslan/local-marketplace (2 stars, last pushed 4mo ago), licensed MIT. It adds 276 tokens to every session and 1,238 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.
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…
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…
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.…
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
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.
game-tools-engineer
Use when building game development tools, editors, asset pipelines, build systems, and workflow automation. Expert in tooling that multiplies team productivity.