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 tance-mang/chinese-webnovel-skills --skill memorygit clone --depth 1 https://github.com/tance-mang/chinese-webnovel-skillsWrote 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/tance-mang/chinese-webnovel-skills/memory)<a href="https://agentmods.dev/skills/tance-mang/chinese-webnovel-skills/memory"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/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/skills/tance-mang/chinese-webnovel-skills/memory"><img src="https://agentmods.dev/badge/skills/tance-mang/chinese-webnovel-skills/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 | $0.00094 | $0.01517 |
| Opus 5.5 | $0.00038 | $0.00607 |
| Sonnet 5.5 | $0.00019 | $0.00303 |
| Haiku 4.5 | $0.00009 | $0.00152 |
Grade A, and why
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 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.
创作档案与记忆系统(memory)
给每本书一套持久化记忆:设定、人物、大纲、伏笔、灵感、进度、投稿记录全存在书的文件夹里,跨会话不丢。像 git 一样可做版本快照、可回顾"写到哪了"。
何时用
- 记录/保存大纲、人设、世界观,下次接着用
- 隔了几天回来续写:"我上次写到哪了?"
- 查"这个伏笔回收没""主角现在什么境界"
- 给书做版本快照、回滚
- 管理多本书的进度
档案结构(书的"记忆")
在书的文件夹里维护这套文件(没有就用本技能初始化):
《书名》/
├── 00_设定.md 立项卡 + 金手指 + 世界观 + 势力库 + 战力体系(book-bible)
├── 01_人物.md 人设卡 + 当前状态 + 语言指纹 + 情绪/关系轨迹 + 弧线
├── 02_大纲.md 卷纲 / 章纲
├── 03_伏笔追踪.md 埋点 → 回收 表(编号/重要度,防烂尾命脉)
├── 04_灵感本.md spark 速记的灵感
├── 05_进度.md 写到第几章 / 累计字数 / 下一步
├── 06_投稿记录.md 每次投稿:平台/日期/结果/拒因/改动
├── 07_时间线.md 主时间线 + 知情人名单 + 世界状态(长篇防失忆)
└── 正文/
├── 第001章.md
└── ……
短篇可只用 00/01/02;长篇务必加 07_时间线 与 战力体系,配合
continuity防写到上百章崩设定。 模板见templates/book-bible-template.md、templates/submission-log-template.md、templates/progress-template.md;格式详见references/project-memory.md。
四个功能
1. 建档(init)
为新书创建上面的档案结构,从模板填入已有信息(调 idea/outline/character 的产出)。
2. 回顾续写(resume)
读 05_进度.md + 02_大纲.md + 03_伏笔追踪.md + 01_人物.md,一句话汇报:
《书名》写到第 N 章(累计 X 万字)
上一章结尾钩:……(本章要回应)
待回收伏笔:……
主角当前状态:……
下一步建议:写第 N+1 章,本章大纲是……
解决"隔几天忘了写到哪"。
3. 更新(update)
写完/改完后同步档案:
- 写完一章 → 更新
05_进度.md(章号/字数/下一步) - 出现新伏笔/回收伏笔 → 更新
03_伏笔追踪.md - 人物状态变化(升级/关系/获得物/伤势) → 更新
01_人物.md - 情绪/关系值变化、人物弧线推进 → 更新
01_人物.md情绪轨迹(防"刚失恋下章笑哈哈") - 时间推进 / 谁知道了什么秘密 / 世界状态变化(战争/损毁/势力更替)→ 更新
07_时间线.md - 战力变化(境界突破/新强敌登场) → 更新
00_设定.md战力对照 - 新灵感 → 追加
04_灵感本.md
不回写就会"下一章继续漂"——这是防失忆的闭环。要主动核对前后矛盾用
continuity;强设定题材先搭世界用world。
4. 版本快照(像 git)
两种方式,按用户情况推荐:
- 真·git(推荐,能回滚看历史):在书的文件夹
git init,每次定稿章节后git add . && git commit -m "第N章定稿"。本技能可代为执行。想回到旧版本git log+git checkout。 - 轻量快照(不用 git):把关键文件复制成带日期版本,如
02_大纲_2026-06-05.md,留存历史版本。
原则
- 档案记录已确认事实,区分大纲计划、待采用草稿与作者定稿。续写前同时核对最近作者修订的正文;档案冲突时指出证据,不用旧摘要覆盖新正文。只有已采用版本中的变化才回写。
03_伏笔追踪.md是防烂尾命脉,每章必查必更。- 多本书各自独立文件夹,互不干扰。
- 未发布稿件是否被忽略需实际检查,不能保证
.gitignore已排除。只暂存本次明确要保存的书稿文件,不默认git add .;回滚先查看差异并保留作者未提交修改,不直接覆盖工作稿。
配合
spark写灵感本、outline写大纲、character写人物(含语言指纹)、submission写投稿记录 —— 本技能统管这些档案的回顾与版本。continuity读本档案核对逻辑/时间线/战力一致性 —— 记忆负责"记",continuity 负责"核对"。- 全书篇幅/字数规划 →
references/length-standards.md。
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 · +6 lines 0bc5af68df09
- 2mo ago First seen · 78 lines · 94 tokens per session scan A 847024c840dd
memory is a skill published in the GitHub repository tance-mang/chinese-webnovel-skills (97 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 1,517 once invoked, about $0.0004 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 2026-08-30.
memory compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| memorytance-mang/chinese-webnovel-skills | Skill | 97 | yesterday | MIT | A | 94 | Claude Code |
| learn-from-fixoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 46 | Claude Code |
| assigns-auditoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 47 | Claude Code |
| recalloliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 64 | Claude Code |
| compound-docsoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 38 | Claude Code |
| evolving-statusclaude-world/director-mode-lite | Skill | 80 | 16d ago | MIT | A | 17 | Claude Code |
| session-recapsxhmilyoyo/sundayhao-plugins | Skill | 9 | yesterday | Apache-2.0 | A | 39 | Claude Code |