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 prefab-reference-repairgit 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/prefab-reference-repair)<a href="https://agentmods.dev/skills/tyunta/prefab-sentinel/prefab-reference-repair"><img src="https://agentmods.dev/badge/skills/tyunta/prefab-sentinel/prefab-reference-repair.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.00606 |
| Opus 5 | $0.00051 | $0.00303 |
| Sonnet 5 | $0.00020 | $0.00121 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
prefab-reference-repair 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 8d 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
Prefab Reference Repair
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
Detect and repair broken references while avoiding unsafe auto-fixes.
Workflow
validate_refsMCP ツールで missing assets / fileIDs を特定する。find_referencing_assetsで壊れた参照の使用箇所を調査する。- 一意で決定的な置換先が存在すれば
safe_fixを提案する。 - 複数候補がある場合は
decision_requiredとして保留する。 - ノイズの多い missing GUID は
validate_refsのignore_asset_guidsパラメータで除外し、<scope>/config/ignore_guids.txtを更新する。 validate_refsを再実行してスコープがクリーンになったことを確認する。
MCP ツール
validate_refs— 壊れた GUID/fileID 参照のスキャン（scope,ignore_asset_guidsパラメータ）find_referencing_assets— GUID/パスの参照元アセット検索（asset_or_guid,scopeパラメータ）
Guardrails
- Do not edit YAML directly.
- Only apply
safe_fixwhen the candidate is unique and unambiguous. - Ignore-guid updates in CI are restricted to allowlisted branches.
次にこれ
- 置換先が決まったら
/prefab-sentinel:variant-safe-editでset_property/patch_applyを dry-run → confirm の経路に乗せる。 - 修復後にランタイム例外が再発したら
/prefab-sentinel:udon-log-triageで再分類する。 validate_refs/find_referencing_assetsの引数や挙動を確認したいときは/prefab-sentinel:guideと docs/tools.md 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.
- 8d ago First seen · 40 lines · 101 tokens per session scan A 281b88b0c18e
prefab-reference-repair is a skill published in the GitHub repository tyunta/prefab-sentinel (11 stars, last pushed 23d ago), licensed MIT. It adds 101 tokens to every session and 606 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
Guide for graphics API interception, overlay rendering, and render-pipeline analysis across DirectX, OpenGL, and Vulkan. Use this skill when working with Present or SwapBuffers hooks, DXGI swap chains, shader or draw-call interception, screenshot-sensitive overlays, or graphics debugging in game security research.
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.