skill

skill is a skill for Claude Code, Codex from Project-N-E-K-O/N.E.K.O. It costs 0 tokens per session (613 once invoked), scanned A, original, Apache-2.0.

A set of design and implementation rules for N.E.K.O plugin modules. It covers plugin structure, asynchronous code, error handling, storage, configuration, translations, communication between plugins, and events.

In plain words
What is it for?
Use it when building or reviewing N.E.K.O plugin code, especially its entry points, settings, data storage, translations, and event handling.
Why use it?
It reduces inconsistent plugin behavior and common runtime problems. It also defines the required patterns for lifecycle handlers, results, file access, localization, and cross-plugin calls.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building or reviewing N.E.K.O plugin code, especially its entry points, settings, data storage, translations, and event handling.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/project-n-e-k-o/n.e.k.o/skill
About the project

N.E.K.O is a real-time AI catgirl companion designed to live with the user, initiate interaction, share media, and perform tasks through an emotional engine. It is intended for people seeking a proactive personal digital companion. The catalogue contains skills for working with it.

Project-N-E-K-O/N.E.K.O · 2,774 stars · on GitHub · store.steampowered.com

Install

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.

Any agent
npx skills add Project-N-E-K-O/N.E.K.O --skill skill
Clone the repo
git clone --depth 1 https://github.com/Project-N-E-K-O/N.E.K.O

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 skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/project-n-e-k-o/n.e.k.o/skill.svg)](https://agentmods.dev/skills/project-n-e-k-o/n.e.k.o/skill)
Your own site
<a href="https://agentmods.dev/skills/project-n-e-k-o/n.e.k.o/skill"><img src="https://agentmods.dev/badge/skills/project-n-e-k-o/n.e.k.o/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 613 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00000 $0.00613
Opus 5 $0.00000 $0.00307
Sonnet 5 $0.00000 $0.00123
Haiku 4.5 $0.00000 $0.00061

Measured 8d ago against content hash ae9030890d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

skill 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 8d 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.

plugin/plugins/bilibili_danmaku/skill/SKILL.md · 25 lines

What it actually says

N.E.K.O 插件模块设计原则(自动遵循)

一、基础架构(强制)

  1. 类装饰器:必须使用 @neko_plugin,类继承 NekoPluginBase
  2. 生命周期:至少实现 @lifecycle(id="startup")@lifecycle(id="shutdown"),返回 Ok / Err
  3. 入口点:使用 @plugin_entry 装饰,必须包含 **_ 参数,返回 Ok(...)Err(SdkError(...)),禁止直接返回 dict 或抛异常。
  4. Result 类型:所有跨插件调用、可能失败的内部操作都返回 Ok / Err,消费时用 isinstance(result, Ok)unwrap_or

二、代码风格(硬性)

  1. 对称性:多个同类组件(如不同 TTS provider)必须保持目录结构和处理路径对称,不得出现数字后缀(如 _2)。
  2. 异步非阻塞:在 async 函数中禁止同步文件 IO、同步 SQLite、同步 HTTP、CPU 密集循环、time.sleep。文件 IO 用 atomic_write_*_async / read_json_async;SQLite 用 a* 版本;HTTP 用 httpx.AsyncClient;CPU 密集用 await asyncio.to_thread(...)
  3. 日志规范:使用 self.logger 输出调试/信息/警告。任何涉及用户原始对话的内容必须用 print,不得用 logger
  4. i18n 同步:修改用户可见字符串时,必须同时更新 en.json, ja.json, ko.json, zh-CN.json, zh-TW.json, ru.json 六个文件,缺一不可。

三、数据与存储

  1. 持久化:使用 PluginStore 做键值存储,或 self.data_path() 获取 data/ 目录下的文件(如 self.data_path("cache.db"))。
  2. 配置:插件自身配置放在 self.config_dir / "config.json",使用 PluginConfig 读取。

四、跨插件与事件

  1. 跨插件调用:通过 self.plugins.call_entry("other_plugin:entry_id", args),必须检查返回的 Err
  2. 事件总线self.bus.emit() 发布事件,self.bus.on() 订阅(通常在 startup 中订阅)。
  3. 定时任务:使用 @timer_interval,注意共享状态加锁(threading.Lockasyncio.Lock)。

五、目录与部署

  1. 目录结构
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. 8d ago First seen · 25 lines · 0 tokens per session scan A ae9030890d88

Subscribe to this mod's changes

skill is a skill published in the GitHub repository Project-N-E-K-O/N.E.K.O (2,774 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 613 tokens. 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.