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-brainstormgit clone --depth 1 https://github.com/devdavv/unity-ai-workflowWhat 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 | $0.00540 |
| Opus 5 | $0.00000 | $0.00270 |
| Sonnet 5 | $0.00000 | $0.00108 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
uw-cmd-brainstorm 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/uw-cmd-brainstorm — Ideation Workflow
Transform a rough game idea into structured design document sections.
Steps
1. Understand the Vision
Present this to the user before they answer:
Structure your answer using TCREI for the best results:
- T — Task: What exactly do you want this game to do?
- C — Context: Genre, platform, target audience, mood, tone.
- R — References: 2-3 games that inspire this. What specifically do you like about each?
- E — Evaluate: After my first response, tell me what's right, wrong, or missing.
- I — Iterate: We'll refine from there.
Then ask:
- What is the one-sentence pitch for this game?
- What is the core fantasy — what does the player feel?
- Name 3 reference games that capture elements of what you want.
- What platform(s) are you targeting?
2. Define the Core Loop
Build the fundamental loop together:
Input -> Action -> Feedback -> Reward -> Loop
Ask: "What does the player do most often? What makes that action satisfying?"
3. Write Gherkin Scenarios
Convert each mechanic into Given/When/Then:
Scenario: Player jumps
Given the player is grounded
When the player presses the jump button
Then the player moves upward with force 10
And a dust VFX plays at the player's feet
And a jump SFX plays
4. Populate GDD Sections
Fill in GDD template sections: Core Loop Definition, Mechanics (Gherkin), Entity & Balance Data tables, Input Mapping.
When suggesting mechanics, visual styles, or feel patterns — always cite the reference game or source. Example: "A cascade system like Candy Crush's, where chains trigger a scored multiplier." This helps the user search for videos/screenshots to visualize.
5. Initial GFD Pass
For each mechanic, ask: "What should the player feel?" and start the Feedback Matrix (VFX, SFX, Camera, Haptics).
When art, audio, or font assets are needed, reference docs/ASSET_RESOURCES.md for curated sources.
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.
- 2d ago First seen · 57 lines · 0 tokens per session scan A 9793567767fb
uw-cmd-brainstorm 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 540 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
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
godot-review
Review a Godot project for structure, architecture, maintainability, and risk.
level-beat
Design or revise level flow, beats, pacing, and encounter structure.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
start-platform
启动/停止 GameServer 排行榜服务(:22333).
play-dashboard
Play in the dashboard — the local viewer becomes your play surface, with a live AI DM beside it.