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/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-doctor)<a href="https://agentmods.dev/commands/xeldaralz/everything-claude-unity/unity-doctor"><img src="https://agentmods.dev/badge/commands/xeldaralz/everything-claude-unity/unity-doctor.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 5.1 | $0.00026 | $0.01059 |
| Opus 5 | $0.00013 | $0.00530 |
| Sonnet 5 | $0.00005 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
unity-doctor 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 8d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/unity-doctor — Diagnostic Health Check
Run a comprehensive diagnostic check on the everything-claude-unity installation and the Unity project. Report each check as PASS, WARNING, or ERROR with actionable fixes.
Check 1: Unity MCP Server Connectivity
- Attempt to call
project_infovia MCP to get Unity version and project state. - If it succeeds: report Unity version, platform, and play mode state → PASS
- If it fails: report the error → ERROR with suggestions:
- Is the unity-mcp package installed in Unity?
- Is the Unity Editor running and the project open?
- Is the MCP server running on the expected port?
- Check
.claude/settings.json→mcpServers.unityMCP.url
Check 2: .claude/ Directory Integrity
- Verify expected directories exist:
commands/,agents/,hooks/,skills/,rules/ - For each hook in
hooks/: check the file exists and is executable (-xpermission) - For each command in
commands/: verify it has YAML frontmatter withnameanddescription - For each agent in
agents/: verify it has YAML frontmatter withname,description,model, andtools - Check
.claude/VERSIONfile exists and report version number - Report counts: X commands, Y agents, Z hooks, W skills, V rules
- Any missing directories → ERROR; any invalid frontmatter → WARNING; all good → PASS
Check 3: Hook Registration Completeness
- Read
.claude/settings.json - For every
.shfile inhooks/directory (excluding_lib.sh):- Check it is registered in either
PreToolUseorPostToolUsein settings.json - Report unregistered hooks → WARNING
- Check it is registered in either
- For every hook path in settings.json:
- Check the referenced file exists
- Report missing files → ERROR
- Verify blocking hooks (
block-*.sh) are inPreToolUseand warning hooks (warn-*.sh,validate-*.sh,suggest-*.sh) are inPostToolUse - All correct → PASS
Check 4: Unity Project Structure
- Check for
Assets/directory → ERROR if missing - Check for
ProjectSettings/directory → ERROR if missing - Check for
Packages/manifest.json→ WARNING if missing - Check for
CLAUDE.mdin project root → WARNING if missing, suggest/unity-init - Search for
.asmdeffiles inAssets/→ WARNING if none found - Search for test assembly definitions (
*Tests*.asmdef) → WARNING if none, suggest/unity-test - All present → PASS
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.
- 8d ago First seen · 93 lines · 26 tokens per session scan A 9941506af967
unity-doctor is a command published in the GitHub repository XeldarAlz/everything-claude-unity (22 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,059 once invoked, about $0.0001 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
build-fix
Incrementally fix build errors one at a time.
debug
Systematic debugging process to isolate and fix issues.
lint-fix
Auto-fix lint and formatting issues across the codebase.
story-continue
Resume an interrupted story from where you left off.
nds-test
Read the knowledge base BEFORE any MCP tool call.
fix-issue
Analyze and fix the GitHub issue: $ARGUMENTS.