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 LiPu-jpg/Openwrite --skill novel-reviewergit clone --depth 1 https://github.com/LiPu-jpg/OpenwriteWrote 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/lipu-jpg/openwrite/novel-reviewer)<a href="https://agentmods.dev/skills/lipu-jpg/openwrite/novel-reviewer"><img src="https://agentmods.dev/badge/skills/lipu-jpg/openwrite/novel-reviewer/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/lipu-jpg/openwrite/novel-reviewer"><img src="https://agentmods.dev/badge/skills/lipu-jpg/openwrite/novel-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.01120 |
| Opus 5 | $0.00024 | $0.00560 |
| Sonnet 5 | $0.00010 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
novel-reviewer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
小说审查润色
通过 openwrite-bridge 的 novel_* 工具评审与修订。不要调用 Python 审查类或本地 33 维脚本。
正式评审是六域累加：质量分、覆盖率、硬门禁、交付状态分开判断；37 项只作展开查询。
触发条件
- "检查逻辑" / "逻辑检查"
- "润色" / "润色风格"
- "找伏笔漏洞" / "伏笔检查"
- "审查章节" / "审查"
- "风格问题"
工作流程
novel_outline_read与novel_status确认章节与项目阶段。novel_chapter_work读取正文 revision、已有评审新鲜度、本章伏笔义务。novel_review_framework需要时查看六域与 37 项映射。novel_review_chapter对已有正文跑六域评审（可传chapter_id或稿件路径）。- 向作者报告质量分、覆盖率、门禁、交付状态，以及带正文证据的问题。
- 作者要改稿：
novel_revision_create_from_review（或选区novel_revision_create_selection）→ 展示 before/after → 确认后novel_revision_apply。 - 应用后必须
novel_review_chapter复评；正文 SHA 变了旧评审即 stale。 - 润色类局部修改走
novel_document_change_plan预览/确认，不直接整章覆盖。
工具
| 工具 | 用途 |
|---|---|
novel_review_framework |
六域 / 37 项框架 |
novel_review_chapter |
正式评审（长耗时） |
novel_chapter_work |
评审新鲜度、闭合结果、伏笔 |
novel_revision_create_from_review |
从问题生成修订提案 |
novel_revision_create_selection |
从选区生成修订 |
novel_revisions_list / novel_revision_get |
查看提案 |
novel_revision_apply / novel_revision_reject / novel_revision_regenerate |
应用、驳回、重生成 |
novel_document_change_plan |
手工/润色类正文预览确认 |
novel_continuity |
连续性、关系、未回收伏笔 |
六域（计分）与硬门禁
| 域 | 权重 | 关注 |
|---|---|---|
| 连贯与逻辑 | 20 | 时间线、因果、信息传播 |
| 人物与关系 | 15 | 动机、声音、关系 |
| 情节与承诺 | 20 | 伏笔、支线、情感账单 |
| 节奏与场景 | 15 | 章内节奏、场景完成度 |
| 文笔与表达 | 15 | AI 痕迹、信息倾倒、句式 |
| 正典与引用 | 15 | 设定、专名、前文事实 |
| 硬门禁 | 不计分 | 严重 blocker；只改 gate_status |
问题不扣质量分。inconclusive 降低覆盖率。交付要求：质量与覆盖达阈值、门禁未阻断、评审源 SHA 等于当前正文 SHA。
报告给作者看的结构
章节 / 字数 / 评审 revision
质量分 · 覆盖率 · 门禁 · 交付
证据条目（原文定位 + 建议）
本章伏笔：到期 / 超期 / 待埋入（来自 novel_chapter_work）
下一步：生成修订 / 驳回 / 复评
定位不唯一时标记失效，不要把错误原文高亮成证据。过期评审必须先复评。
错误处理
| 情况 | 处理 |
|---|---|
| 尚无正文 | 提示先写章，不要空审 |
| 评审 stale | 先 novel_review_chapter，禁止对旧问题直接 apply |
| 提案源 revision 不匹配 | novel_revision_regenerate 或重新预览 |
| 后台任务进行中 | novel_task_get 轮询，不要重复提交 |
与其他技能
- novel-creator：写章后进入本技能
- dog-review-query / dog-delivery-query：查询已物化评审/交付图，不重新调用模型
- truth-validation：正典与事实核对
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.
- 2d ago Changed · -224 lines 8ffbf6c304c2
- 12d ago First seen · 308 lines · 49 tokens per session scan A 3a7642ec26ba
novel-reviewer is a skill published in the GitHub repository LiPu-jpg/Openwrite (715 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,120 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 skills, from other repositories
awesome-novel
A nine-agent workflow for writing a novel with AI, from creating the initial setting through organizing the finished material. It can also bring an existing novel into the workflow.
audit-playbook
A code-security audit playbook covering source-code review, runtime checks, software dependencies, deployment settings, and AI-agent security risks.
ida-reversing
Perform reverse engineering and binary analysis in IDA Pro using natural language commands powered by IDA MCP. Use this skill whenever the user wants to: analyze executable files, understand function behavior, decompile code, explore cross-references, search for strings or bytes, patch binary code, document reverse…
workflow
A command set for starting and managing step-by-step automated workflows.
local-search
A local search component that finds web results using installed command-line tools and page parsers. It supports general web search and extra sources for areas such as Chinese pages, news, code questions, academic work, and reference material.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…