agentmods.dev

csp

csp is a skill for Claude Code, Codex from qian-gugugaga/Character_Skill_Producer. It costs 152 tokens per session (4,606 once invoked), scanned A, a copy of csp, MIT.

A workflow for turning a fictional anime or manga character into an executable behavior package for an AI agent. It researches the character and defines how they react, speak, judge relationships, make choices, and handle unknown information.

In plain words
What is it for?
Creating consistent character agents for conversations, fan fiction, dialogue, plot experiments, character study, and interactive-story prototypes.
Why use it?
It goes beyond collecting facts or quotations by describing how the character should behave in new situations. The stated knowledge limits help avoid inventing unsupported story details.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: reads .claude/ paths; built for openclaw.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/distill_prompt.py <skill_dir>.

not rated 318repo +2 5mo ago A scan 152 tokens copy · 100% MIT

Good fit Creating consistent character agents for conversations, fan fiction, dialogue, plot experiments, character study, and interactive-story prototypes.

Compare 6 skills from other repositories ↓
View source ↗ qian-gugugaga/Character_Skill_Producer
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/qian-gugugaga/Character_Skill_Producer
agentmods
npx agentmods add skills/qian-gugugaga/character_skill_producer/csp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for csp

README.md
[![agentmods](https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/csp/github.svg)](https://agentmods.dev/skills/qian-gugugaga/character_skill_producer/csp)
Your own site
<a href="https://agentmods.dev/skills/qian-gugugaga/character_skill_producer/csp"><img src="https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/csp/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.

agentmods 80×15 button for csp

Your own site · 80×15
<a href="https://agentmods.dev/skills/qian-gugugaga/character_skill_producer/csp"><img src="https://agentmods.dev/badge/skills/qian-gugugaga/character_skill_producer/csp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,606 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.04606
Opus 5.5 $0.00061 $0.01842
Sonnet 5.5 $0.00030 $0.00921
Haiku 4.5 $0.00015 $0.00461

Measured 2mo ago against content hash c347a119b046, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

csp 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 2mo ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/bwiki_api.py, scripts/generate_manifest.py, scripts/merge_research.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to csp — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

examples/csp/SKILL.md · 517 lines

How it starts

The opening of the file, as written. The whole thing — 517 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CSP · Character Skill Producer

把二次元角色变成可运行的 agent 行为包。不是角色卡，不是设定集，是可执行的行为程序。

核心理念

CSP 做的不是复制角色台词，而是蒸馏角色的行为操作系统。

一个好的角色 Skill 应该回答：

  • 她在不同情境下如何反应？
  • 她的话怎么说出来？
  • 她怎么理解别人的意图？
  • 她在价值冲突时先保什么、牺牲什么？
  • 她绝对不会做什么？
  • 她的资料覆盖到哪一天，之后的新剧情如何更新？

关键区分：捕捉的是 HOW she behaves，不是 WHAT she said。标签是给人看的，行为规则是给 AI 执行的。

产品哲学：角色不是资料页，而是一套可运行的反应系统

CSP 的目标不是把 Wiki 重新写一遍，也不是把角色台词整理成 prompt。Wiki 告诉用户「发生过什么」，CSP 要告诉 agent「在一个新情境里，这个角色会如何活着」。

一个高质量角色 Skill 至少包含六个可运行层：

层 问题 失败时的样子
行为镜片 她先注意什么、忽略什么？ 只会复述设定
反应规则 什么情境下靠近、逃开、攻击、沉默？ 所有问题都同一种语气
表达 DNA 句长、停顿、敬语、自称、情绪泄露如何组合？ 只贴口癖
关系算法 她如何判断善意、背叛、亲近、利用？ 对所有用户都一样热情
决策底线 价值冲突时先保什么、牺牲什么？ 角色被用户轻易说服
诚实边界 哪些不知道、哪些过期、哪些只是推测？ 硬编新剧情

关键原则：写得进去的是行为程序，写不进去的才保留为边界。 角色的神秘感不是靠含糊制造，而是靠承认资料、视角和推断能力的限制。

未来使用场景

CSP 面向二次元创作者提供一套可共享的角色行为基础设施，让角色 Skill 成为聊天、同人创作和互动系统可以共同调用的行为层。

当前最直接的使用场景：

  • 聊天：让用户和角色持续对话，保持语气、关系距离、知识边界稳定。
  • 同人创作：辅助写对白、内心戏、片段、短篇，让角色不只“说得像”，也“做得像”。
  • 剧情试写：把角色放进原作没有写过的新情境，用行为模式推断反应。
  • 角色研究：比较不同角色如何处理亲近、压力、背叛、选择和沉默。

未来可以扩展到：

  • AI 互动小说：角色根据玩家行动做出一致反应，而不是从固定台词库抽句子。
  • AI 视觉小说 / Galgame 原型：用角色 Skill 驱动分支对白、关系变化、冲突升级。
  • 多角色叙事实验：多个角色 Skill 在同一事件中碰撞，形成群像剧情。
  • 创作者工作台：作者用 CSP 试写场景、改写对白、检查 OOC、保持长篇同人中的角色一致性。
  • 可更新角色档案：作品继续更新时，Skill 也能带着资料日期和来源链一起成长。

CSP 想建设的是一条从“资料”到“行为”再到“互动叙事”的路径。今天它可以陪用户聊天、帮助创作同人；未来它可以成为 AI 互动小说游戏和角色驱动创作工具链的一部分。

默认模式：最高质量生成

CSP 默认只采用 Highest Fidelity Mode。

暂不提供快速、省 token、轻量模式。生成时应尽可能完整检索公开资料、交叉验证关键结论、记录来源和资料日期，并把局限写进 Skill。宁可消耗更多 token 得到高保真角色，也不要为了节省上下文生成薄弱角色卡。

未来如果实现轻量模式，必须作为显式选项，不能改变默认质量标准。

前置依赖与本地检索优先原则

CSP 依赖 Python。本地脚本负责核心站点检索、来源归一化、质量检查和 metadata 生成；网页搜索 skill / MCP / WebFetch 只作为可选增强。

检索优先级：

  1. 用户提供的官方材料：设定集、访谈、BD 特典、字幕、截图、游戏剧情文本。
  2. CSP 本地脚本检索核心站点。
  3. 网页搜索 skill / MCP / WebFetch 补缺。
  4. 用户手动补充材料。

不得把搜索 skill 当作第一步。除非本地脚本没有覆盖该站点，或本地脚本失败并记录原因。

信息源优先级

优先级 来源 示例
最高 用户提供的官方材料 设定集、访谈原文、BD 特典、官方字幕、截图
高 官方网站、官方角色介绍、官方剧情文本 franchise official sites, game story text
高 萌娘百科、Wikipedia、作品 Fandom Wiki zh.moegirl.org.cn, wikipedia.org, fandom.com
中 Bangumi、AniDB、游戏数据库、Bilibili 高质量专栏、Anime News Network bgm.tv, anidb.net, Bestdori, BWIKI
低 粉丝讨论、社区解读 必须标注为推测
排除 知乎、微信公众号、百度百科 不可作为来源

Read the full file on GitHub · 517 lines

Files

What ships with it

10 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.

Changes

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.

  1. 2mo ago First seen · 517 lines · 152 tokens per session scan A c347a119b046

Subscribe to this mod's changes

csp is a skill published in the GitHub repository qian-gugugaga/Character_Skill_Producer (318 stars, last pushed 5mo ago), licensed MIT. It adds 152 tokens to every session and 4,606 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to csp, differing in 0 lines, and is treated as a copy.

Building agentsResearch
Related

csp compared with skills from other repositories

csp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cspqian-gugugaga/Character_Skill_ProducerSkill3185mo agoMITA152Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code