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 agentmods add skills/waylean/plotrail/plotrail-intakenpx skills add waylean/plotrail --skill plotrail-intakegit clone --depth 1 https://github.com/waylean/plotrailWhat 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 | $0.00144 | $0.01658 |
| Opus 5 | $0.00072 | $0.00829 |
| Sonnet 5 | $0.00029 | $0.00332 |
| Haiku 4.5 | $0.00014 | $0.00166 |
Grade A, and why
plotrail-intake 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PlotRail Intake
Use this skill for existing prose. Treat the manuscript as evidence, not approved canon, until the user approves extracted facts or the project already marks them as accepted.
PlotRail Intake is the editor and intake layer for PlotRail. It helps an agent read existing chapters, diagnose problems, refine text conservatively, extract reusable story state, learn author style, audit continuity, and prepare compact handoff briefs for PlotRail (plotrail).
Core Rule
Preserve author intent and remove AI-flavored prose by default. Do not silently rewrite plot outcomes, core character motivation, relationship direction, timeline, genre promise, voice, or approved canon. Do not imitate a living author's distinctive style; use named authors only as high-level craft anchors such as pacing, scene pressure, dialogue economy, information release, concrete texture, or hook design. Separate:
- text-confirmed manuscript facts
- inferred but uncertain facts
- approval status for transferred facts
- editorial diagnosis
- proposed edits
- final revised prose
If an edit changes canon, relationship direction, ending direction, power rules, or the author's likely intent, stop and ask for approval.
Mode Selection
Choose the smallest mode that answers the user:
- Cold-start pasted prose - The user pasted one chapter, excerpt, or long handwritten passage. Read
references/intake-protocol.md. - Chapter diagnosis - The user asks what is weak or how to improve a chapter. Read
references/diagnosis-rubric.md. - Chapter correction or refinement - The user asks to correct, 校正, polish, 润色, make better, edit, revise, or rewrite existing prose. First run the minimum pass from
references/intake-protocol.md, then readreferences/refinement-workflow.md. - Manuscript intake - The user provides multiple chapters or a folder before continuation. Read
references/intake-protocol.md. - Style learning - The user asks to learn voice, compare original/revised drafts, or build an editing profile. Read
references/style-learning.md. - Long-form audit - The user asks for consistency across chapters. Read
references/continuity-audit.md. - Handoff to PlotRail writing - The next step is planning or drafting with PlotRail (
plotrail). Readreferences/plotrail-handoff.mdandreferences/shared-context.md.
What ships with it
9 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.
- agents/openai.yaml 281 B
- references/anti-ai-prose.md 4.5 KB
- references/continuity-audit.md 2.0 KB
- references/diagnosis-rubric.md 3.0 KB
- references/intake-protocol.md 3.5 KB
- references/plotrail-handoff.md 2.9 KB
- references/refinement-workflow.md 3.4 KB
- references/shared-context.md 4.2 KB
- references/style-learning.md 2.4 KB
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.
- yesterday First seen · 153 lines · 144 tokens per session scan A ede84fc1b589
plotrail-intake is a skill published in the GitHub repository waylean/plotrail (11 stars, last pushed 2mo ago), licensed MIT. It adds 144 tokens to every session and 1,658 once invoked, about $0.0007 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
novel-writing
Use when planning, drafting, revising, or reviewing fiction where character anchoring, viewpoint drift, implausible knowledge or decisions, unnatural dialogue, scene or chapter continuity, style fidelity, or grounded physical and institutional causality matter.
story-import
逆向导入已有小说。将已写好的小说（半成品或完本）反向解析为标准项目目录结构，兼容 story-long-write / story-short-write 后续写作流程；内部复用 story-long-analyze / story-short-analyze 的拆解管道，按篇幅自动分流。触发方式：/story-import、「导入小说」「反向解析」「导入」「把我的书导进来」。.
story-review
多视角对抗式审查。full/lean 模式在已部署 reviewer agents 时并行 spawn；缺失/异常 agents 或 spawn 失败时自动降级 solo，参考文件不可读时使用内置 rubric fallback。触发方式：/story-review、/审查、「审查一下」「帮我审一下」。.
story-short-write
短篇网文写作。辅助短篇小说创作，从构思到成稿，聚焦情绪拉扯与节奏把控。触发方式：/story-short-write、/写短篇、「帮我写一篇短篇」「写个盐言故事」。.
story-deslop
网文去AI味。检测并清除文本中的AI写作痕迹，让文字回归自然、非模板化。触发方式：/story-deslop、/去AI味、「去AI味」「这篇太AI了」「网文去AI味」。.
story-long-analyze
长篇网文拆文。深度拆解爆款长篇小说的黄金三章、人设架构、爽点设计、节奏控制。单一深度拆解管道：跑完黄金三章（Stage 1）后产出快速预览报告并询问是否继续全量拆解，确认后从 Stage 2 续跑逐章摘要、聚合分析、设定关系、汇总报告，全程产物落盘 拆文库/{书名}/。触发方式：/story-long-analyze、/长篇拆文、「帮我拆这本书」「拆这本书」「分析黄金三章」「深度拆解」「完整拆解」「系统拆解」或提供小说文本文件路径——全部进入同一管道。.