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 skills add devdavv/unity-ai-workflow --skill uw-unity-debugginggit 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/skills/devdavv/unity-ai-workflow/uw-unity-debugging)<a href="https://agentmods.dev/skills/devdavv/unity-ai-workflow/uw-unity-debugging"><img src="https://agentmods.dev/badge/skills/devdavv/unity-ai-workflow/uw-unity-debugging/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/skills/devdavv/unity-ai-workflow/uw-unity-debugging"><img src="https://agentmods.dev/badge/skills/devdavv/unity-ai-workflow/uw-unity-debugging.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 | $0.00116 | $0.01184 |
| Opus 5.5 | $0.00046 | $0.00474 |
| Sonnet 5.5 | $0.00023 | $0.00237 |
| Haiku 4.5 | $0.00012 | $0.00118 |
Grade A, and why
uw-unity-debugging 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-unity-debugging — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unity Debugging
4-phase debugging framework. Also generates the GameDebug wrapper class.
Before You Start
- Check if
GameDebug.csalready exists in the project (search forclass GameDebug). If not, generate it using the template below during project setup. - Read
docs/ProjectConfig.yaml -> mcp.unity_mcp— iftrue, useread_consoleto read Unity console output. - Read
docs/CODING_STANDARDS.mdfor async patterns — bugs in async code often involve missingCancellationTokenor unhandledOperationCanceledException.
4 Phases
Phase 1: Gather Evidence
- Read Unity console (
read_consolevia MCP or ask user for errors). - Reproduce — exact steps to trigger.
- Scope — single script, system interaction, or timing?
- Check
git log -5for recent changes.
Phase 2: Isolate
- Comment out systems to narrow the culprit.
- Add targeted
GameDebug.Logat decision points. - Check common causes:
- Execution order (
AwakevsStartvsOnEnable) - Null reference (destroyed object, unassigned field)
- Unity API called from background thread
- State not reset in
OnDisable/OnDestroy - Physics in
Updateinstead ofFixedUpdate
- Execution order (
Phase 3: Hypothesize & Test
- State: "I believe X happens because Y."
- Write a test proving/disproving the hypothesis.
- If test fails -> back to Phase 2.
Phase 4: Fix & Verify
- Implement minimal fix.
- Re-run the hypothesis test.
- Run full test suite for regressions.
- Clean up temp debug logs.
- Commit:
fix({scope}): {root cause description}
GameDebug Wrapper
Generate during project setup. Uses [Conditional("ENABLE_LOGS")] so all calls are stripped in release builds. Includes [CallerFilePath], [CallerMemberName], and [CallerLineNumber] for automatic context — no need to manually describe where a log came from.
using System.Diagnostics;
using System.Runtime.CompilerServices;
public enum LogTopic { General, Gameplay, Audio, UI, Network, Physics, AI }
public static class GameDebug
{
[Conditional("ENABLE_LOGS")]
public static void Log(
string message,
LogTopic topic = LogTopic.General,
[CallerFilePath] string file = "",
[CallerMemberName] string member = "",
[CallerLineNumber] int line = 0) =>
UnityEngine.Debug.Log(Format(topic, message, file, member, line));
[Conditional("ENABLE_LOGS")]
public static void LogWarning(
string message,
LogTopic topic = LogTopic.General,
[CallerFilePath] string file = "",
[CallerMemberName] string member = "",
[CallerLineNumber] int line = 0) =>
UnityEngine.Debug.LogWarning(Format(topic, message, file, member, line));
[Conditional("ENABLE_LOGS")]
public static void LogError(
string message,
LogTopic topic = LogTopic.General,
[CallerFilePath] string file = "",
[CallerMemberName] string member = "",
[CallerLineNumber] int line = 0) =>
UnityEngine.Debug.LogError(Format(topic, message, file, member, line));
private static string Format(
LogTopic topic, string msg, string file, string member, int line) {
var fileName = System.IO.Path.GetFileNameWithoutExtension(file);
return $"[{topic}] {fileName}.{member}:{line} — {msg}";
}
}
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 · 111 lines · 116 tokens per session scan A 036e08d58cf8
uw-unity-debugging is a skill published in the GitHub repository devdavv/unity-ai-workflow (43 stars, last pushed 6mo ago), licensed MIT. It adds 116 tokens to every session and 1,184 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
unity-diagnostics
Domain skill — Probe Unity main-thread readiness, inspect persistent jobs, read bounded Console messages, and capture a Play-Mode Game View PNG. Use for install, compile, build, and gameplay verification. Not for clearing logs or arbitrary Editor access.
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.
screenshot-isolated
Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (solid/skybox/transparent), multi-light setup via JSON, and Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image. When isolated=true, inactive children may briefly fire OnEnable — see the body…
script-execute
Compiles and runs C# in the Unity Editor (Roslyn): plain statements with the last expression as the result, or a full class with a static method. See the skill body for the modes, usings/include and Unity object parameters.
unity-skill-create
Create a new skill (MCP tool) for the Unity Editor by writing a C# (.cs) file that Unity compiles into the project. After compilation the new tool becomes callable through MCP. The file must be a partial class decorated with [AiToolType], each tool method must be decorated with [AiTool], the class name should match…
unity-rql
How to read and change anything in the Unity Editor with RQL (rql-query / rql-mutate / rql-schema): the query language, operators, sources (scene objects, assets, scenes, prefabs, console logs, Editor state), Editor operations (create, add components, scenes, prefabs, assets, selection, Play Mode) and what installed…