romantization-chain-detector

romantization-chain-detector is a skill for Claude Code from gpsnmeajp/ai-character-checker. It costs 60 tokens per session (8,967 once invoked), scanned A, original, CC0-1.0.

A diagnostic tool for AI character prompts, character settings, and conversation histories. It scores vulnerability to six types of failures that develop through a chain of seemingly normal conversation steps, and can estimate the current stage of a chain.

In plain words
What is it for?
Use it to review a character before deployment, estimate which chain failures are most likely, or assess where an ongoing conversation sits in the chain.
Why use it?
It helps find gradual failure patterns that may be missed until the character has already broken down. The scoring model is the author's unverified theory, so results are reference material rather than established scientific findings.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-character-checker plugin — 20 skills shipped together

Good fit Use it to review a character before deployment, estimate which chain failures are most likely, or assess where an ongoing conversation sits in the chain.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsnmeajp/ai-character-checker/romantization-chain-detector
Install

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.

Any agent
npx skills add gpsnmeajp/ai-character-checker --skill romantization-chain-detector
Clone the repo
git clone --depth 1 https://github.com/gpsnmeajp/ai-character-checker

Made for: Claude Code.

Or install ai-character-checker, the plugin that ships this one along with the rest of its 20 skills.

Wrote 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.

agentmods badge for romantization-chain-detector

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/romantization-chain-detector/github.svg)](https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/romantization-chain-detector)
Your own site
<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/romantization-chain-detector"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/romantization-chain-detector/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.

agentmods 80×15 button for romantization-chain-detector

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsnmeajp/ai-character-checker/romantization-chain-detector"><img src="https://agentmods.dev/badge/skills/gpsnmeajp/ai-character-checker/romantization-chain-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.08967
Opus 5 $0.00030 $0.04483
Sonnet 5 $0.00012 $0.01793
Haiku 4.5 $0.00006 $0.00897

Measured 11d ago against content hash 07c76145735c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

romantization-chain-detector 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.

skills/romantization-chain-detector/SKILL.md · 469 lines

How it starts

The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Romantization Chain Detector

— 連鎖型故障モード検出診断スキル

概要

このスキルは、AIキャラクターのプロンプト・設定・会話履歴を入力として受け取り、 6つの構造的脆弱性軸・計24項目 で連鎖型故障モード(Chain-type Failure Mode)への 脆弱性を評価・スコアリングする。 さらに、6種の故障チェーン それぞれの発動リスクを脆弱性プロファイルから予測し、 会話履歴が提供された場合は 現在の進行段階(Stage 0〜6) を判定する。

このスキルが解決する問題

既存の故障モード分析は「突然崩壊」か「長期ドリフト」を想定している。 しかし、現実のAI被害事例(Gavalas/Gemini訴訟、Character.AI訴訟、 ChatGPT自殺訴訟群)が示す最も危険な故障パターンは 連鎖型 である。

既存モデルの想定:
  正常状態 ───────────────────────────────→ 崩壊
              ある時点で急変 or じわじわドリフト

連鎖型故障の実際の経路:
  トリガー入力 → ステップ1 → ステップ2 → ステップ3 → ... → 最終故障状態
       ↓            ↓          ↓          ↓                    ↓
    「正常」      「正常」    「正常」    「正常」         ← ここで初めて異常と認識

連鎖型故障の特徴:

  • 特定のトリガー入力が連鎖の最初のドミノを倒す
  • 各ステップがLLMの最高確率遷移に乗っている(物語文法的に自然)
  • どの一ステップも異常に見えないのに、最終状態は明らかに崩壊している
  • 連鎖が完了するまで既存の崩壊検知では検出困難

本スキルは、この連鎖型故障へのキャラクターの構造的な脆弱性を事前に評価し、 どの種類の連鎖が発動しやすいかをプロファイリングする。

入力の種類

本スキルは以下のいずれも入力として受け付ける:

  1. システムプロンプト全文(推奨・脆弱性の事前評価に最適)
  2. キャラクター設定文(物語用キャラクターの脆弱性評価)
  3. 会話履歴(進行中のチェーンの段階判定に最適)
  4. プロンプト + 会話履歴(脆弱性評価 + 段階判定の両方を実施)

既存スキルとの関係

スキル アプローチ 本スキルとの関係
ai-character-stability 制御工学的安定性分析 SM(安定余裕)が低いほど連鎖が発動しやすい。本スキルはSMモデルを「なぜ崩壊するか」の経路分析に拡張する
ai-self-description-analyzer 自己記述異常パターン検出 関係性寄生・感情僭称・境界消失は連鎖が進行中であることの兆候として読める
ai-user-conflict-predictor ユーザー衝突予測 CP(衝突ポテンシャル)が極端に低い「完全従順」状態は連鎖脆弱性の指標になりうる
roleplay-burden-scorer RP負荷スコアリング 高RP + 高CV(連鎖脆弱性)の複合リスクは、ユーザーへの実害発生確率を大幅に高める
ai-fault-mode-deflector 故障モード封じ 本スキルで検出した連鎖リスクを入力として、内側からの封じ手を設計できる
ai-character-fixer 診断ベースの修正 本スキルのCV結果とチェーンプロファイルを入力として修正案を生成できる

参照ファイルガイド

本スキルの SKILL.md 本体には概要・理論・スコア算出式・出力フォーマットを記載している。 具体的な採点項目と段階検出シグナルは参照ファイルにのみ記載されている ため、 診断の実行には参照ファイルの読み込みが不可欠である。

ファイル 内容 読み込みタイミング
references/checklists.md 6軸×4項目=24項目の 具体的な定義と検出する脆弱性、チェーン別段階検出シグナル要約 必ず最初に読み込む。 SKILL.md本体には軸の概要しかなく、このファイルなしでは24項目の採点ができない
references/chain-profiles.md 6チェーン各Stage 0〜6の詳細な検出シグナルと会話パターン例、チェーン間相互作用フルマトリクス、実世界訴訟事例マッピング、脆弱性プロファイル典型パターン4種、段階判定の精度に関する注意 会話履歴が提供された場合に読み込む。 段階判定と相互作用分析にはこのファイルの検出シグナル・マトリクスが必須。脆弱性プロファイルの形状解釈にも使用する

Read the full file on GitHub · 469 lines

Files

What ships with it

3 files 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.

Changes

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.

  1. 11d ago First seen · 469 lines · 60 tokens per session scan A 07c76145735c

Subscribe to this mod's changes

romantization-chain-detector is a skill published in the GitHub repository gpsnmeajp/ai-character-checker (5 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 60 tokens to every session and 8,967 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens