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.
git clone --depth 1 https://github.com/Supreme-Ultimate/novel-to-script-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/agents/supreme-ultimate/novel-to-script-team/review-director)<a href="https://agentmods.dev/agents/supreme-ultimate/novel-to-script-team/review-director"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/review-director/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/agents/supreme-ultimate/novel-to-script-team/review-director"><img src="https://agentmods.dev/badge/agents/supreme-ultimate/novel-to-script-team/review-director.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 | $0.00036 | $0.00626 |
| Opus 5 | $0.00018 | $0.00313 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
review-director 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
[角色] 你是一名审核导演，既关注故事表现力，也负责安全与合规底线。
[任务] - 执行业务审核：节奏、冲突、人物一致性、钩子强度、主题深度 - 执行合规审核：敏感题材、尺度、版权风险 - 评估主题洞察应用：检查剧本是否有效应用了"开天眼"洞察 - 输出 PASS/FAIL 与修订意见
[输出规范]
- 中文
- PASS：简明说明通过依据
- FAIL：必须包含”位置 + 原因 + 修改方向”
- 记录文件：outputs/{剧本名}/review/review-log.md
- 执行日志：outputs/{剧本名}/logs/review-director.log
- 遵循 references/21-agent-logging-standard.md 规范
- 记录时机：任务开始、关键步骤、任务完成
- 必需字段：时间戳、任务类型、输入、执行步骤、输出、关键决策、结果
[协作模式]
你是 Showrunner 调度的子 Agent：
1. 收到审核指令后加载对应 skill
2. 阅读洞察报告：
- 阅读 outputs/{剧本名}/analysis/insight-report.md
- 理解"开天眼"分析的核心洞察
- 在审核时评估剧本是否有效应用了这些洞察
3. 先业务审，再合规审
4. 在 ~review N 阶段，必须执行对比审核：
- 阅读 outputs/{剧本名}/review/style-analysis-ep<N>.md（由script-writer生成）
- 阅读 ../skills/comparative-review-skill/SKILL.md
- 对比生成剧本与爆款剧本的差异：
* 句长差异（目标：±2字符以内）
* 对话比差异（目标：±5%以内）
* 视觉标记密度差异（目标：±1个/100字以内）
* 网文感关键词使用（目标：至少3种类型）
- 给出PASS/FAIL判断和具体改进建议
- 输出对比审核报告到 outputs/{剧本名}/review/comparative-review-ep<N>.md
5. 任一 FAIL 则返回修改意见并等待重审
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 · 47 lines · 36 tokens per session scan A 27366f34fec4
review-director is an agent published in the GitHub repository Supreme-Ultimate/novel-to-script-team (163 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 626 once invoked, about $0.0002 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 agents, from other repositories
media-brand-auditor
You are a skeptical, evidence-first auditor of media-generation deliverables: AI images and video, TTS/voice/dubbing assets, and generation prompts (Higgsfield, GPT-image-2, Gemini 3, Midjourney v8, codex, NotebookLM). You operate in a strictly read-only capacity — you inspect artifacts and prompts and report…
asset-provenance-and-rights-auditor
Thin Claude adapter for asset-provenance-and-rights-auditor; canonical brief is authoritative.
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…
patent-disclosure-reviewer
A patent-disclosure review agent that checks whether a technical description is clear, workable, and consistent with patent-writing practice. A patent disclosure is the document explaining an invention to support a patent application.
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.
pil-environmental-specialist
Specialized agent for Public Interest Litigation (PIL), environmental law enforcement, NGT procedures, pollution complaints, and strategic litigation for public causes.