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/devdavv/unity-ai-workflow/uw-cmd-reviewgit clone --depth 1 https://github.com/devdavv/unity-ai-workflowWrote 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/devdavv/unity-ai-workflow/uw-cmd-review)<a href="https://agentmods.dev/commands/devdavv/unity-ai-workflow/uw-cmd-review"><img src="https://agentmods.dev/badge/commands/devdavv/unity-ai-workflow/uw-cmd-review.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 | $0.00000 | $0.00433 |
| Opus 5 | $0.00000 | $0.00217 |
| Sonnet 5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
uw-cmd-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 3d 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
/uw-cmd-review — Code Review Pass
Run a structured quality review on implemented code before it is committed.
Note: This is a Unity-specific review. For general code review, Claude Code also offers native PR review via GitHub App integration.
Skills
Load uw-code-review from .claude/skills/uw-code-review/SKILL.md.
Steps
1. Identify Scope
Ask (or infer from context):
"Which file(s) or feature should I review? Or should I review everything changed since the last commit?"
In autonomous mode: infer from recent changes (git diff) and proceed.
2. Read Target Files
Read all specified files. Also read:
docs/GDD.md— to verify Gherkin scenario coveragedocs/GFD.md— to verify game feel status (integrated or TODO filed)
3. Run Code Review Checklist
Apply the full uw-code-review checklist:
- CLAUDE.md rules compliance
- Naming conventions
- Code quality
- Performance anti-patterns
- Test coverage (Gherkin -> NUnit mapping)
- Game feel (integrated or TODO filed)
4. Output Structured Report
## Code Review — {FeatureName or FileList}
### Rules Compliance [Pass | Issues]
### Naming [Pass | Issues]
### Code Quality [Pass | Issues]
### Performance [Pass | Issues]
### Test Coverage [X/Y scenarios | Missing]
### Game Feel [Integrated | TODO filed | Missing]
Issues to fix before commit:
- [list each issue with file and line, or "None"]
5. Resolve Issues
- In autonomous mode: fix flagged issues immediately, then re-run.
- In guided mode: present the report, wait for user confirmation, then fix.
Only mark the review complete when Issues to fix is "None".
6. Output
- Clean review report (all green)
- Code ready to commit
$ARGUMENTS
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.
- 3d ago First seen · 58 lines · 0 tokens per session scan A 85a6aed8c07f
uw-cmd-review is a command published in the GitHub repository devdavv/unity-ai-workflow (41 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 433 tokens. 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
README
This folder maps Claude-facing command use to the shared /commands layer.
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
combat-design
Design or revise combat rules, variables, readability, and tuning direction.
godot-review
Review a Godot project for structure, architecture, maintainability, and risk.
level-beat
Design or revise level flow, beats, pacing, and encounter structure.
orchestrate
Coordinate multiple agents to solve a complex cross-discipline task.