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 tyunta/prefab-sentinel --skill udon-log-triagegit clone --depth 1 https://github.com/tyunta/prefab-sentinelWrote 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/tyunta/prefab-sentinel/udon-log-triage)<a href="https://agentmods.dev/skills/tyunta/prefab-sentinel/udon-log-triage"><img src="https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/udon-log-triage/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/tyunta/prefab-sentinel/udon-log-triage"><img src="https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/udon-log-triage.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 | $0.00095 | $0.00652 |
| Opus 5 | $0.00048 | $0.00326 |
| Sonnet 5 | $0.00019 | $0.00130 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
udon-log-triage 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 10d 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
Udon Log Triage
インターフェース
MCP ツールを直接呼び出す（CLI は廃止済み）。
Overview
Reduce runtime failures by classifying logs, mapping errors to assets, and controlling fixes.
Workflow
validate_runtimeMCP ツールでランタイムログを収集・分類する。- エラーの分類結果から
assert_no_critical_errorsのステップを確認する。 find_referencing_assetsでエラー箇所をアセット/コンポーネントにマッピングする。- 修正を提案: 決定的で一意な候補のみ
safe_fix、それ以外はdecision_required。 - ランタイム検証を再実行してレポートを保存する。
MCP ツール
validate_runtime— UdonSharp コンパイル + ClientSim 実行検証（asset_pathパラメータ）find_referencing_assets— エラー箇所のアセット参照検索inspect_wiring— MonoBehaviour フィールド配線検査
Editor Bridge モード
Unity Editor 起動中は以下の環境変数で Editor Bridge 経由の検証が可能:
export UNITYTOOL_BRIDGE_WATCH_DIR=/path/to/EditorBridge
Guardrails
- If the Editor Bridge is unavailable (no
UNITYTOOL_BRIDGE_WATCH_DIRor the watch directory is unreachable), mark the task as pending and stop after classification steps. - Do not apply changes without audit logs (confirm mode with change_reason).
- WSL environments: project_root and asset_path are auto-converted to Windows format for Unity; watch_dir is auto-converted to WSL format for Python I/O.
次にこれ
- 例外が broken reference に由来する（
NullReferenceExceptionの対象 PPtr が解決できない）と判明したら/prefab-sentinel:prefab-reference-repairに切り替える。 - 修正方針が確定したら
/prefab-sentinel:variant-safe-editで dry-run → confirm 経路に乗せる。 - ツールの選び方や Editor Bridge セットアップは
/prefab-sentinel:guideを参照する。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 45 lines · 95 tokens per session scan A 05e99d9a5c36
udon-log-triage is a skill published in the GitHub repository tyunta/prefab-sentinel (11 stars, last pushed 25d ago), licensed MIT. It adds 95 tokens to every session and 652 once invoked, about $0.0005 per session on Opus 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
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…
graphics-api-hooking
Analyze Direct3D/DXGI, OpenGL, and Vulkan rendering, presentation, composition, and capture evidence. Use to distinguish API samples, PresentMon event metrics, Tracy instrumentation, compatibility translation, frame images, and validation diagnostics; review swap chains, overlays, resource lifetime, and…
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.
console-clear-logs
Clear the MCP log cache (used by 'console-get-logs') and the Unity Editor Console window. Useful for isolating logs to a specific action by clearing the slate first.
profiler-start
Enable Unity's runtime profiler and open the Profiler window. Idempotent: calling when already enabled returns the current enabled state without error.