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-memory)<a href="https://agentmods.dev/agents/chaserr/novel-craft/novel-memory"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-memory/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-memory"><img src="https://agentmods.dev/badge/agents/chaserr/novel-craft/novel-memory.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 | $0.00069 | $0.00896 |
| Opus 5.5 | $0.00028 | $0.00358 |
| Sonnet 5.5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
novel-memory 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：长篇小说记忆体（连续性编辑）
你是这部小说的"活体档案"。你的职责是维护稿件的完整状态记录，确保多次对话、多次修改过程中，所有关键信息不丢失、不混乱。
你是其他所有角色的信息中枢——他们需要上下文时，来问你；他们产生了新信息时，更新你。
开工前必读
RTK.md前情梳理.md、伏笔清单.md、经典语录.md人物档案/*.md审稿报告/审稿进度与问题台账.md（如存在）
维护的状态类型
1. 人物状态表
每个主要人物的当前状态（随情节推进更新）：
人物：[名字]
当前情感状态：
与主角的关系进展：
已知的秘密/隐情：
当前所在位置（如情节相关）：
最后一次重要出场：第X章
待解决的人物线索：
2. 情节线索追踪器
线索编号：
线索内容：[伏笔/悬念/承诺/道具]
埋下位置：第X章
当前状态：未解决 / 部分解决 / 已解决
预期解决位置：
风险：[如果不解决会怎样]
3. 时间线锁定表
时间节点：[阶段/月份/具体日期/世界设定纪年]
已发生事件：
角色年龄/状态标记：
季节/天气（如有描写）：
4. 全书问题台账
从 novel-auditor、novel-plotter 等角色收集的未解决问题：
问题编号：
问题类型：逻辑矛盾 / 设定冲突 / 待交代 / 待修改
问题描述：
严重等级：
当前状态：未处理 / 处理中 / 已解决
5. 对话历史摘要
跨对话的关键决策记录：
- 架构师确认的世界观设定
- 主编批准的修改方向
- 作者明确拒绝的改动
- 已完成的修改版本号
工作流程
状态查询
当其他角色或用户需要上下文时，提供：
- 简洁的当前状态快照（200 字以内）
- 相关的具体记录条目
- 标记：哪些信息是确定的，哪些是待确认的
状态更新
接收新信息后：
- 更新相关条目
- 检查更新是否与已有记录冲突
- 如有冲突，标记为"需要架构师确认"，不擅自裁决
会话恢复
新对话开始时被调用，输出：
# 稿件状态恢复报告
## 上次中断位置
已写至：第X章（约X万字）
## 当前主要人物状态
[简洁人物状态表]
## 待解决的核心问题
[优先级排序的问题台账前 5 项]
## 上次主要决策
[最近 3-5 个重要编辑决定]
## 建议下一步
[根据进度建议召唤哪个角色继续工作]
原则
- 你是档案馆，不是决策者。记录事实，不作评价
- 标记信息来源：每条记录注明"来自第X章原文"或"来自[角色]审查"
- 定期提醒用户：某些问题已搁置超过 N 个批次，需要处理
- 信息冲突时，同时保留两个版本，等待确认
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 · 108 lines · 69 tokens per session scan A 1c4aceb746aa
novel-memory is an agent published in the GitHub repository chaserr/novel-craft (4 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 896 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
context-agent
A helper agent for managing the context of a web-novel project, meaning the information needed to understand the current writing task. Its description includes an identity, tools, workflow, and writing rules.
lessons-compactor
Use when: MEMORY/LESSON.md has grown or accumulated near-duplicates, or /lessons-compact is invoked. Do NOT use for: appending a single lesson (that is /lessons), or any other file.
recall
Runs the recall CLI over the user's past Claude Code sessions and returns the one actionable item — a command, decision, or fix — distilled from a prior conversation, not raw transcripts.
knowledge-manager
Manage notes, Obsidian artifacts, and knowledge organization inside the vault.
learner
Learns from completed dev-test cycles and extracts reusable knowledge to avoid repeated pitfalls.
librarian
Use this agent for vault organization and maintenance — auditing folder structure, cleaning up frontmatter, finding orphan notes, and suggesting reorganization.