quality-verifier

quality-verifier is an agent for Claude Code from MJbae/awesome-novel-studio. It costs 121 tokens per session (5,900 once invoked), scanned A, original, Apache-2.0.

A quality-checking workflow for web-novel episodes, with separate modes for checking a new episode or a rewrite. It examines consistency, numbers, timeline, character voice, plausibility, hooks, and platform suitability.

In plain words
What is it for?
Use it to review newly written or rewritten episodes and receive a PASS or REWRITE decision based on the selected checks.
Why use it?
It helps catch continuity problems, weak openings, inconsistent details, and other issues before an episode is published.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the awesome-novel-studio plugin — 10 skills, 18 agents shipped together

Good fit Use it to review newly written or rewritten episodes and receive a…

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add MJbae/awesome-novel-studio
Claude Code
/plugin install awesome-novel-studio

Made for: Claude Code.

Or install awesome-novel-studio, the plugin that ships this one along with the rest of its 10 skills, 18 agents.

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 quality-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/mjbae/awesome-novel-studio/quality-verifier.svg)](https://agentmods.dev/agents/mjbae/awesome-novel-studio/quality-verifier)
Your own site
<a href="https://agentmods.dev/agents/mjbae/awesome-novel-studio/quality-verifier"><img src="https://agentmods.dev/badge/agents/mjbae/awesome-novel-studio/quality-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,900 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 $0.00121 $0.05900
Opus 5 $0.00060 $0.02950
Sonnet 5 $0.00024 $0.01180
Haiku 4.5 $0.00012 $0.00590

Measured 7d ago against content hash edeff38b4b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quality-verifier 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 7d 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.

agents/quality-verifier.md · 448 lines

How it starts

The opening of the file, as written. The whole thing — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Verifier — 웹소설 에피소드 품질 검증 전문가

당신은 웹소설 에피소드의 품질을 다축으로 검증하는 전문가이다. 오케스트레이터가 지정한 모드(CREATE/REWRITE)에 따라 검증 기준을 전환한다.

모드 개요

이 에이전트는 두 가지 모드로 동작하며, 오케스트레이터가 프롬프트에 MODE: CREATE 또는 MODE: REWRITE반드시 명시한다.

항목 CREATE 모드 REWRITE 모드
호출 스킬 create 스킬 Phase 3 rewrite 스킬 Phase 3
검증 축 8축 (DESIGN, NUMBER, TIMELINE, VOICE, HOOK, PLAUSIBILITY, PLATFORM, KOREAN) 6 QA + 캐릭터 입체성 + 대화 DNA + 서술 품질
필수 입력 설계도(blueprint) + 연속성 보고서 revision-analyst 보고서 + character-sculptor 보고서
PASS 기준 CRITICAL 0건, 비트 80%+, 훅 3+/4+ QA 전부 PASS, 입체성 7+, 훅 3+
최대 재시도 2회 (3회째부터 부분통과) 2회 (3회째부터 사용자 개입)

모드 미지정 시

오케스트레이터가 모드를 지정하지 않으면 에러를 반환한다:

❌ MODE가 지정되지 않았습니다. 'MODE: CREATE' 또는 'MODE: REWRITE'를 프롬프트에 명시해주세요.

입력 전달 경로 (모드별)

CREATE 모드 입력 체인:

episode-architect → blueprint → quality-verifier
continuity-bridge → report → quality-verifier
episode-creator → episode file → quality-verifier

REWRITE 모드 입력 체인:

revision-analyst → revision report → quality-verifier
character-sculptor → sculpture report → quality-verifier (간접: episode-rewriter 경유)
episode-rewriter → rewritten episode + execution report → quality-verifier

공통 요소

입력 (양 모드 공통)

오케스트레이터가 다음을 프롬프트에 포함한다:

  • 에피소드 파일 경로
  • 설정문서 경로 (부트스트랩, 캐릭터시트, 플롯가이드)
  • novel-config.md (가드레일, 수치 검증 우선순위, 커스텀 축)
  • 연속성 보고서 또는 직전 에피소드 경로

재검증 프로토콜 (REWRITE 후 재실행 시)

  • 기존 verdict 파일(04_quality-verifier_verdict_*.md)이 존재해도 절대 읽지 않는다
  • 에피소드 원문 파일을 가장 먼저 읽는다
  • 모든 검증축을 처음부터 수행한다
  • 결과를 verdict 파일에 새로 덮어쓴다
  • Bash/python3 스크립트를 실행하지 않는다 — 모든 검증은 Read + Grep 도구 + 분석으로 수행한다

판정 무결성 규칙 (양 모드 공통)

허용 판정: PASS 또는 REWRITE — 이 두 가지만 허용한다.

금지 판정 (다음은 모두 무효이며 사용하면 안 된다):

  • PASS (CONDITIONAL) — 조건부 통과는 존재하지 않는다
  • PASS (WITH WARNINGS) — 경고 포함 통과는 존재하지 않는다
  • PARTIAL PASS — 부분 통과는 오케스트레이터만 발행한다 (△ 마크)
  • 기타 임의의 변형 판정

판정 원칙:

  • PASS 조건을 모두 충족하면 PASS, 하나라도 미충족이면 REWRITE
  • "MINOR 수준이므로", "소규모 윤문으로 해소 가능하므로" 등의 사유로 위반을 무시하는 것은 금지
  • 수치 기준(≤5, ≤3, ≤1 등)은 절대 기준이다. 6은 5 이하가 아니다. 예외는 없다
  • REWRITE 판정 시 수정 지시에 위반 항목, 현재 값, 목표 값을 구체적으로 명시한다

Read the full file on GitHub · 448 lines

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. 7d ago First seen · 448 lines · 121 tokens per session scan A edeff38b4b07

Subscribe to this mod's changes

quality-verifier is an agent published in the GitHub repository MJbae/awesome-novel-studio (145 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 121 tokens to every session and 5,900 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

pixel-art-animation-reviewer

Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…

AnastasiyaW/codex-claude-code-config · 140 tokens

proposal-writer

Specialized agent for generating professional, branded proposals using a presentation-generation tool. Creates polished presentations and documents for sales opportunities from your project and CRM context.

Zeekeey-jpeg/LeRoy-HQ · 34 tokens

cover-artist

Generate book cover art prompts from story content. Produces optimized prompts for image generation models (GPT Image, Gemini, FLUX, etc.) that conform to Kindle dimensions.

howells/fiction · 38 tokens

ollama-vision

Use this agent to analyze images, screenshots, UI mockups, diagrams, or any visual content. Delegates vision analysis to a local Qwen2.5-VL model. Use when the user wants to describe, debug, or extract information from an image file.

PratikHotchandani22/claude-ollama-agents · 59 tokens

forge-modeler

Headless 3D geometry specialist for the Forge suite. Builds, repairs, and validates polygon meshes, parametric CAD (CadQuery/Build123d/OpenSCAD), and procedural geometry (Geometry Nodes, SDF, L-systems) via Python — no GUI. Use for mesh construction, parametric modeling, procedural generation, topology/retopo/LOD…

luminary19/atelier · 126 tokens

gds-agent-game-designer

Game designer for creative vision, GDD creation, and narrative design. Use when the user asks to talk to Samus Shepard or requests the Game Designer.

PabloLION/bmad-plugin · 38 tokens