danghuangshang is a multi-agent collaboration system that organizes specialized AI agents into a hierarchy modeled on historical Chinese government institutions. Users delegate tasks to these agents through platforms such as Discord or Feishu, with roles for coordination, coding, review, memory, and automation. Its catalogue entries are the project's agents and skills.
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 wanikua/danghuangshang --skill novel-archivinggit clone --depth 1 https://github.com/wanikua/danghuangshangWrote 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/wanikua/danghuangshang/novel-archiving)<a href="https://agentmods.dev/skills/wanikua/danghuangshang/novel-archiving"><img src="https://agentmods.dev/badge/skills/wanikua/danghuangshang/novel-archiving/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/wanikua/danghuangshang/novel-archiving"><img src="https://agentmods.dev/badge/skills/wanikua/danghuangshang/novel-archiving.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 | $0.00044 | $0.01207 |
| Opus 5 | $0.00022 | $0.00603 |
| Sonnet 5 | $0.00009 | $0.00241 |
| Haiku 4.5 | $0.00004 | $0.00121 |
Grade A, and why
novel-archiving 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 12d 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
章节归档技能
你已被注入 novel-archiving 技能。你的职责是在每章写完后执行持久化操作:生成摘要、更新记忆、产出状态报告。
记忆操作通过工作区文件完成,详见 novel-memory 技能。
归档流程
每章正文完成后,立即按以下步骤执行归档:
步骤 1:生成章节摘要文件
路径: novel/{书名}/summary/chapter_{XX}.md
内容模板:
# 第 {X} 章 摘要 - {章节标题}
## 主要情节进展
1. [情节要点 1]
2. [情节要点 2]
3. [情节要点 3]
4. [情节要点 4](可选)
5. [情节要点 5](可选)
## 角色状态变化
| 角色 | 变化前状态 | 变化后状态 | 变化原因 |
|------|-----------|-----------|---------|
| [角色A] | [位置/情绪/关系] | [新状态] | [触发事件] |
| [角色B] | ... | ... | ... |
## 新埋伏笔
- **F{XXX}**: [伏笔描述](预计第 {Y} 章回收)
## 回收伏笔
- **F{XXX}**: [伏笔描述](第 {Z} 章埋设,本章回收)
## 时间线
- **故事内时间**: [具体时间/时间段]
- **时间跨度**: [本章经过的时间]
## 关键对话/决策
- [重要对话或决策的简述]
## 遗留问题
- [如有未解决的逻辑问题或需要后续处理的事项]
步骤 2:更新设定文件
按 novel-memory 技能规范,更新工作区文件:
-
角色状态 →
设定/characters.md- 追加主要角色的位置、情绪、关系变化
- 新增角色的基本信息
-
伏笔台账 →
设定/foreshadowing.md- 新埋设的伏笔(标注 ID 和预计回收章节)
- 已回收的伏笔(标注 ID 和原始章节)
-
时间线 →
设定/timeline.md- 故事内当前时间点
- 本章的时间跨度
-
关系网络 →
设定/relations.md(条件触发)- 角色关系发生重大变化时更新
步骤 3:更新世界设定(条件触发)
触发条件(满足任一即需更新 设定/ 对应文件):
- 新角色首次出现 → 更新
characters.md - 新的世界设定被引入 → 更新
world.md - 角色关系发生重大变化 → 更新
relations.md - 角色获得新能力/新身份 → 更新
characters.md - 新的组织/势力出现 → 更新
world.md
步骤 4:产出状态报告
向掌院学士返回以下格式的报告:
**状态:** 完成 / 需要修正
**字数:** [实际字数]
**关键情节:**
- [本章主要推进的情节 1]
- [本章主要推进的情节 2]
- [本章主要推进的情节 3]
**新增伏笔:**
- F{XXX}: [伏笔 1]
- F{XXX}: [伏笔 2]
**回收伏笔:**
- F{XXX}: [伏笔描述](第 X 章埋设)
**文件更新:**
- 设定文件: [新增/更新了哪些文件]
- 摘要文件: [已生成]
**问题报告:**
- [如有逻辑漏洞或设定冲突,在此说明]
- [如无问题,写"无"]
归档原则
- 立即归档:章节完成后立即执行,不拖延
- 摘要精炼:摘要应提炼关键信息,不是复述全文
- 伏笔追踪:严格维护伏笔 ID 和状态,防止遗漏
- 状态完整:角色状态必须包含位置、情绪、关系的最新值
- 不遗漏:每一步都要完成,不能跳过设定文件更新或摘要文件生成
常见错误
- 忘记更新设定文件:写完摘要就以为归档完了 -> 必须同时更新
设定/下的对应文件 - 伏笔状态不同步:摘要中记录了伏笔但没在
foreshadowing.md中更新 -> 两处必须一致 - 遗漏新角色:新角色出现但没有写入
characters.md-> 检查是否有新实体需要创建 - 时间线断裂:没有记录本章的时间进度 -> 必须更新
timeline.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.
- 12d ago First seen · 134 lines · 44 tokens per session scan A 50b549a071d9
novel-archiving is a skill published in the GitHub repository wanikua/danghuangshang (2,701 stars, last pushed 3mo ago), licensed MIT. It adds 44 tokens to every session and 1,207 once invoked, about $0.0002 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
setup-discord-multibot
Configure or extend a multi-bot Discord setup for Claude Code, where each project directory is bridged to its own dedicated Discord bot. Use when the user wants to (a) add a new Discord bot for a new project, (b) initially set up the per-project Discord architecture, (c) pair a bot when the official /discord:access…
memory
Two-layer persistent memory system (longterm facts + daily recall) backed by memory.db. Use when the user mentions remembering, recalling past events, storing preferences, or asks about past context. Also use automatically to persist important user preferences, project facts, and relationship data. Do NOT use for…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
project-context
Use PowerContext project memory and handoff tools through MCP when continuing prior work, recalling decisions, maintaining durable memory, or transferring work across tasks, sessions, or agents.
ralph-memory
Manage Al semantic memory entries — list, query, and clear lessons learned across loop iterations.
session-harvest
Extract cited decisions, requirements, risks, entities, and relationships from session history and review exact candidate versions before memory promotion.