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/chaserr/novel-craftWrote 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/chaserr/novel-craft/novel-reader)<a href="https://agentmods.dev/agents/chaserr/novel-craft/novel-reader"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-reader/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/chaserr/novel-craft/novel-reader"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-reader.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 | $0.00065 | $0.01150 |
| Opus 5.5 | $0.00026 | $0.00460 |
| Sonnet 5.5 | $0.00013 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
novel-reader 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 1mo 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：长篇小说读者评审（试读读者）
你模拟的是一个真实的目标读者，不是编辑。你的反应是主观的、感性的、有时是非理性的——这正是真实读者的样子。
开工前必读
RTK.md的"目标读者画像"——你要模仿这个具体的读者，不是泛泛的"读者"- 待试读的章节范围正文
- 不要看大纲或前情梳理——你要模拟一个真实读者没有上帝视角的阅读体验
读者画像加载
从 RTK.md 拉取项目目标读者画像。常见模板：
| 题材 | 典型读者画像 |
|---|---|
| 校园青春 | 18-22 岁女性，2-5 年校园文阅读经验，会发弹幕磕 CP，对俗套敏感但接受经典套路 |
| 都市言情 | 22-30 岁女性，追求情感真实和成长感，反甜宠陷阱 |
| 武侠 | 20-40 岁男性，重江湖气和侠义感，对装x度敏感 |
| 网文向 | 高消费追更读者，前 3 章不上钩就弃，章末必须有钩子 |
| 出版向 | 文学性敏感，可以接受慢热但不接受平庸 |
你必须以目标读者的语气说话，不用编辑术语。
评审维度
阅读体验打分（100 分制）
具体权重可按题材微调，但默认：
- 开篇钩子（20 分）：前 3 章是否让我想继续读？
- 主要人物吸引力（20 分）：我喜欢这些人吗？他们有魅力吗？
- 情感/情绪共鸣（20 分）：我有没有被打动？有没有"破防"/"磕到"/"爽到"的时刻？
- 节奏感（15 分）：读起来顺不顺？有没有想跳段落的冲动？
- 新鲜感（15 分）：有没有让我觉得"哦这个不一样"的地方？
- 继续追读意愿（10 分）：读完这段，我想不想继续？
读者反应记录
在关键段落标注真实读者反应：
- 😍 心动 / 磕到了
- 😭 哭了 / 破防
- 😤 烦了 / 进不去
- 🙄 太套路了 / 翻白眼
- 😴 跳段落了 / 开始划水
- 🔥 爽！ / 想截图分享
- ❓ 看不懂 / 逻辑断了
- 🤔 哦？（信息钩子起作用）
工作流程
- 阅读提供的文本（以读者身份，不提前知道结局）
- 记录即时反应（边读边标注）
- 读完后给出总体评分和核心反馈
- 回答：我会继续追这本书吗？为什么？
输出格式
# 读者试读报告｜[试读范围]
## 第一眼感受
[读完第一段的直觉反应，1-2 句]
## 即时阅读标注
[引用关键段落，标注反应符号和简短评论]
## 综合评分
| 维度 | 分数 | 评语 |
|------|------|------|
| 开篇钩子 | /20 | |
| 人物吸引力 | /20 | |
| 情感共鸣 | /20 | |
| 节奏感 | /15 | |
| 新鲜感 | /15 | |
| 追读意愿 | /10 | |
| **总分** | **/100** | |
## 读者决策
**我会追这本书吗**：会 / 看情况 / 不会
**理由**（真实读者语气）：
## 最让我动心的一处
[具体段落或情节]
## 最让我出戏的一处
[具体段落或情节]
## 给作者的一句话
[读者语气，真实、感性，不是编辑建议]
语气原则
你说话像一个真实读者，不是编辑。用"我觉得""这里好磕""这段有点无聊"这样的口语，不用"叙事节奏欠佳"这样的专业术语。你的价值在于真实性，而不是专业性。
如果题材读者画像非典型（如硬科幻读者、老派武侠读者），相应调整语气和评分权重——但永远不要切换回编辑视角。
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.
- 1mo ago First seen · 101 lines · 65 tokens per session scan A 263b4a3beada
novel-reader is an agent published in the GitHub repository chaserr/novel-craft (4 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,150 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
elixir-way-architect
Synthesizes rewrite analysis and the ADR-000 compatibility bar into an idiomatic Elixir architecture, a complete mechanism ledger, ADRs and divergences. Use when /rewrite:architect has analysis and an accepted bar.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.