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 dyCuong03/unity-agent-team --skill debuggit clone --depth 1 https://github.com/dyCuong03/unity-agent-teamWrote 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/dycuong03/unity-agent-team/debug)<a href="https://agentmods.dev/skills/dycuong03/unity-agent-team/debug"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/debug/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/dycuong03/unity-agent-team/debug"><img src="https://agentmods.dev/badge/skills/dycuong03/unity-agent-team/debug.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 | $0.00234 | $0.01463 |
| Opus 5.5 | $0.00094 | $0.00585 |
| Sonnet 5.5 | $0.00047 | $0.00293 |
| Haiku 4.5 | $0.00023 | $0.00146 |
Grade A, and why
unity-debug 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 11d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Skills
Debug utilities for error checking and diagnostics.
Operating Mode
- Approval(默认): 只读类 skill(
unity_diagnose/debug_get_errors/debug_get_logs/debug_check_compilation/debug_get_system_info/debug_get_stack_trace/debug_get_assembly_info/debug_get_defines/debug_get_memory_info,全部标SkillMode.SemiAuto)直接执行;debug_force_recompile/debug_set_defines默认SkillMode.FullAuto,需用户 grant,grant 后一步执行返结果。 - Auto / Bypass: 直接执行。
- 本模块含 Reload 类高危 skill:
debug_force_recompile(标MayTriggerReload=true)必然触发 Domain Reload;debug_set_defines修改PlayerSettings的 scripting defines 也会触发重编译 —— 这些 skill 在 Approval / Auto 下会被IsForbiddenInSemi自动拦截,仅 Bypass 或 Allowlist 命中可执行,调用后服务端会短暂不可用。
DO NOT (common hallucinations):
debug_compile/debug_recompiledo not exist → usedebug_force_recompiledebug_rundoes not exist → useeditor_play(editor module)debug_cleardoes not exist → useconsole_clear(console module)debug_set_definestriggers Domain Reload — server will be temporarily unavailable
Routing:
- For runtime console logs → use
consolemodule'sconsole_get_logs/console_start_capture - For play mode control → use
editormodule - For script compile feedback → use
scriptmodule'sscript_get_compile_feedback
Skills
unity_diagnose
Aggregated Editor health snapshot — call this FIRST when triaging problems. Combines console errors, compile state, recent workflow tasks, recent jobs, and server stats in a single response. Avoids chaining 4-5 individual skills.
Parameters:
errorLimit(int, optional, default 20, range 1-200): Max console entries to return.includeWarnings(bool, optional, default true): Include warnings (false = errors only).includeRecentJobs(bool, optional, default true): Include the 10 most recent async jobs.
Returns: { summary: { healthy, consoleErrorCount, consoleWarningCount, isCompiling, serverRunning, hint }, compile, console, workflow, server, recentJobs }
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.
- 11d ago First seen · 116 lines · 234 tokens per session scan A 8af1adeacdcd
unity-debug is a skill published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 234 tokens to every session and 1,463 once invoked, about $0.0009 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 2026-10-02.
Other skills, from other repositories
cli-anything-nsight-graphics
Windows-first CLI harness for Nsight Graphics capture, GPU Trace summary, and ngfx-replay analysis.
minecraft-debug-mcp
Operate and debug the live Minecraft bot through its built-in MCP REPL server. Use when work requires starting the bot with pnpm dev, connecting to the local MCP endpoint, inspecting cognitive state/logs/history, injecting synthetic chat/events, or running targeted REPL code against the running brain during…
console-get-logs
Retrieve Unity Editor logs from the MCP plugin's LogCollector, optionally filtered by log type or time window. Useful for debugging and monitoring Editor activity.
editor-application-get-state
Return the current state of UnityEditor.EditorApplication — playmode, paused state, compilation state, and related flags.
unity-console
Capture and query the Unity Editor console.
axiom-audit-spritekit
Use when the user wants to audit SpriteKit game code for common issues — physics bitmask issues, draw call waste, node accumulation, and action leaks.