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 commands/xeldaralz/everything-claude-unity/unity-interviewgit clone --depth 1 https://github.com/XeldarAlz/everything-claude-unityWrote 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/commands/xeldaralz/everything-claude-unity/unity-interview)<a href="https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-interview"><img src="https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-interview.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 | $0.00031 | $0.01253 |
| Opus 5 | $0.00015 | $0.00626 |
| Sonnet 5 | $0.00006 | $0.00251 |
| Haiku 4.5 | $0.00003 | $0.00125 |
Grade A, and why
unity-interview 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 4d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/unity-interview — Deep Requirements Interview
Conduct a thorough, multi-phase requirements interview for: $ARGUMENTS
This command produces a comprehensive feature brief BEFORE any code is written. It is deliberately more thorough than the quick clarify phase in /unity-workflow — use this for large or ambiguous features where getting requirements right is critical.
Phase 1: Scope Exploration
Ask the user to define boundaries:
- What does this feature DO? — core behavior, primary use case
- What does this feature NOT do? — explicit exclusions, out-of-scope items
- Who is the user? — player-facing, designer-facing, developer tool?
- What triggers it? — player input, game event, timer, external signal?
- What is the expected output? — visual change, data mutation, event emission, audio?
Summarize scope before proceeding. Ask user to confirm or adjust.
Phase 2: Technical Requirements
Gather project context automatically and ask targeted questions:
- Read
CLAUDE.mdfor project config (Unity version, render pipeline, target platform, packages) - Read
Packages/manifest.jsonto identify available packages - Scan existing assembly definitions to understand project structure
- Ask about:
- Performance budget — target FPS? Memory ceiling? Max draw calls?
- Platform constraints — mobile thermal throttling? WebGL size limits?
- Unity subsystems — physics, UI, animation, audio, networking, addressables?
- Data persistence — does any state need saving? What format?
- Multiplayer — any networked aspects? Authority model?
Phase 3: Edge Case Identification
For each major component identified in Phase 1-2, systematically explore:
- Error states — what happens when things go wrong? (null references, missing assets, network failure)
- Boundary conditions — minimum/maximum values, empty collections, zero-duration timers
- Platform differences — does this behave differently on iOS vs Android? Editor vs build?
- Race conditions — scene transitions, async operations, destruction timing
- Performance under load — what happens with 100x the expected entities/items/particles?
- Undo/reset — can the player undo this action? What happens on scene reload?
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.
- 4d ago First seen · 139 lines · 31 tokens per session scan A 022876bd6711
unity-interview is a command published in the GitHub repository XeldarAlz/everything-claude-unity (21 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,253 once invoked, about $0.0002 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 commands, from other repositories
sim
Run the EmbodiedGen simulation rendering workflow with sim-cli.
speckit.taskstoissues
Command "speckit.taskstoissues" from akiojin/unity-mcp-server, covering ユーザー入力 and 実行手順.
combat-design
Design or revise combat rules, variables, readability, and tuning direction.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
discuss
5-phase requirements-elicitation interview that produces an EARS-validated context/ .md.
tech-debt
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create actionable remediation plans.