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/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-implement-feature)<a href="https://agentmods.dev/commands/devdavv/unity-ai-workflow/uw-cmd-implement-feature"><img src="https://agentmods.dev/badge/commands/devdavv/unity-ai-workflow/uw-cmd-implement-feature/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/commands/devdavv/unity-ai-workflow/uw-cmd-implement-feature"><img src="https://agentmods.dev/badge/commands/devdavv/unity-ai-workflow/uw-cmd-implement-feature.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 | $0.00000 | $0.01549 |
| Opus 5.5 | $0.00000 | $0.00620 |
| Sonnet 5.5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
uw-cmd-implement-feature 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- uw-cmd-implement-feature — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/uw-cmd-implement-feature — Feature Development Loop
Build a feature complete: interrogation -> TDD implementation -> game feel -> documentation — all in one pass.
Skills
Load uw-game-feel-integrator from .claude/skills/uw-game-feel-integrator/SKILL.md.
Why One Loop?
Polish is not Phase 5. Every feature ships complete: code + feel + documentation. A feature is only "done" when it plays well, not just when it compiles. "Too much juice is easier to fix than too little."
Steps
1. Feature Brief
State the feature in one sentence. Get user confirmation before interrogating.
Example: "We're implementing the double-jump mechanic. The player can jump a second time while airborne."
2. Deep Interrogation
Ask the user these questions. Don't skip them — answers shape implementation and feel.
Structure your answers with TCREI for best results:
- T — Task: What exactly should this feature do?
- C — Context: Constraints, current systems it touches, scope
- R — References: Games, repos, tutorials that do this well
- E — Evaluate: After first pass, what's right/wrong/missing?
- I — Iterate: Refine from there
Reference games:
"Name 1-3 games that do this mechanic well. What do you like about how they handle it?"
Code references:
"Do you know of any GitHub repos, Unity packages, or tutorials that implement this? I can use them as a starting point."
Behavior & edge cases:
"What should happen at the limits?"
Scope:
"Is this prototype/spike quality, or production-ready?"
Visual sketch (optional):
If the feature involves new UI or complex flows, offer visual communication tools. Reference
docs/ASSET_RESOURCES.md -> Visual Communication Tools.
3. Game Feel Questions (per-feature GFD pass)
Ask upfront. Don't defer. These answers update the GFD before a line of code is written.
"Let's lock in the feel for this feature now. Answer roughly — we'll tune values during implementation."
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.
- 1mo ago First seen · 137 lines · 0 tokens per session scan A f63911f45f23
uw-cmd-implement-feature is a command published in the GitHub repository devdavv/unity-ai-workflow (44 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,549 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
build-and-compilation
These commands drive the build/compile/test dev loop, plus build configuration: triggering Player builds and reading the resulting BuildReport, switching the active build target, enumerating targets, reading/writing EditorUserBuildSettings, and listing Build Profiles. Several commands are asynchronous: trigger the…
audio-pass
Functional audio review for implementation, mix coverage, clarity, and player feedback.
input-review
Review input handling, device coverage, buffering, and control responsiveness from an engine-neutral perspective.
qa-plan
Build a QA plan, matrix, and exit criteria for the selected scope.
tdd
Apply test-driven development or regression-driven implementation for the current task.
verify
Run a structured verification pass across implementation, quality, and risk.