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 Xiaoyangy/novel-studio --skill novel-pipelinegit clone --depth 1 https://github.com/Xiaoyangy/novel-studioWrote 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/xiaoyangy/novel-studio/novel-pipeline)<a href="https://agentmods.dev/skills/xiaoyangy/novel-studio/novel-pipeline"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-pipeline/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/xiaoyangy/novel-studio/novel-pipeline"><img src="https://agentmods.dev/badge/skills/xiaoyangy/novel-studio/novel-pipeline.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 | $0.00085 | $0.01248 |
| Opus 5 | $0.00043 | $0.00624 |
| Sonnet 5 | $0.00017 | $0.00250 |
| Haiku 4.5 | $0.00009 | $0.00125 |
Grade A, and why
novel-pipeline 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
novel-pipeline:可恢复流水线
按阶段顺序跑完整流程,状态存 output/novel/meta/pipeline.json,已完成的阶段重跑时自动跳过,
从断点继续。流水线只做阶段编排;每个阶段复用对应子命令逻辑,阶段内部还有更细的恢复
(write 走 checkpoint、review/rewrite 按章号),两层恢复叠加。
阶段
cocreate(可选,多轮澄清)→ write(创作)→ review(评审)→ rewrite(重写)→ deliver(交付沉淀:推进台账 + RAG 事实入库 + 交付快照)
默认序列:write,review,rewrite,deliver(假设已有创作指令)。
前置条件
- 已完成首次配置(见
skills/README.md),LLM 可用(先novel-check)。 - 含
cocreate阶段时需要交互终端。
执行
# 标准:给创作指令,跑写作→评审→重写→交付
novel-studio --pipeline --prompt "写一本东方玄幻长篇,主角从边陲小城起步"
# 从文件读创作指令
novel-studio --pipeline --prompt-file ./requirement.md
# 先共创澄清再一条龙(首阶段交互,之后无人值守)
novel-studio --pipeline --stages cocreate,write,review,rewrite,deliver
# 自定义阶段子集
novel-studio --pipeline --prompt "..." --stages write,deliver
# 单阶段评审 / 重写也走 pipeline,可指定章号范围
novel-studio --pipeline --stages review --from 3 --to 8 --budget 5m
novel-studio --pipeline --stages rewrite --from 3 --to 8 --role coordinator
# 中断后再次运行同一命令即从断点继续;要从头重跑用 --restart
novel-studio --pipeline --prompt "..."
novel-studio --pipeline --prompt "..." --restart
参数
| 参数 | 默认 | 说明 |
|---|---|---|
--prompt <text> / --prompt-file <path> |
— | 创作指令(write 阶段用;- 表示 stdin) |
--stages a,b,c |
write,review,rewrite,deliver |
阶段子集与顺序 |
--write-to <n> |
0 |
write 阶段写到指定章节后暂停;0 表示写到全书完结 |
--from <n> / --to <n> |
0 |
review / rewrite 阶段章号范围 |
--budget <dur> |
阶段默认 | review / rewrite 阶段每章 LLM 调用预算 |
--role <name> |
writer |
rewrite 阶段模型角色 |
--restart |
关 | 清空已保存状态,从头重跑 |
恢复语义
- 每个阶段成功返回后还要通过证据校验,才写入
pipeline.json的completed与evidence;失败或证据不足的阶段不标记完成,下次重跑从它继续 write阶段:本书已完结则跳过;已有进度则恢复创作;全新项目用创作指令起新书- 已标记完成的阶段重跑时会先复核证据;若产物被删或 checkpoint 缺失,会清掉完成标记并重跑该阶段
- 证据口径:
write看progress.phase=complete、章节文件和commit_chaptercheckpoint;review看reviews/*.md与meta/review-summary.md;rewrite看章节文件和.pre-rewrite.md备份;deliver看meta/delivery_log.jsonl/meta/delivery_log.md novel-studio --diag会只读报告meta/pipeline.json的证据漂移;真正清标记和重跑只发生在再次执行--pipeline时- 改了
--stages列表会重置进度(保留已捕获的创作指令) - 状态文件用临时文件 + rename 原子写入,写一半崩溃不损坏
--headless --prompt、--review-existing、--rewrite-existing只保留为兼容别名,新任务应直接调用--pipeline
What ships with it
2 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.
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.
- 11d ago First seen · 74 lines · 85 tokens per session scan A bd90d45b6136
novel-pipeline is a skill published in the GitHub repository Xiaoyangy/novel-studio (107 stars, last pushed 2d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,248 once invoked, about $0.0004 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
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
automation
Instructions for managing scheduled tasks through the host's structured automation tool, including reminders, delayed work, recurring checks, and result delivery.
cron
Schedule, list, pause, resume, edit, or run the user's agentica cron jobs with the cronjob tool. Use when asked to remind, schedule a recurring or one-shot task, try a job now, or manage jobs that fire unattended.
automation-guide
A guide for DeterminFlow Cron automations, which run agents or tasks once or on a repeating schedule.
email-assistant
A read-only assistant for reviewing incoming Yandex or Gmail messages from a chat.