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 agentmods add skills/rushengzhou/sid-code/skill-creatornpx skills add rushengzhou/sid-code --skill skill-creatorgit clone --depth 1 https://github.com/rushengzhou/sid-codeWhat 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 | $0.00020 | $0.01755 |
| Opus 5 | $0.00010 | $0.00877 |
| Sonnet 5 | $0.00004 | $0.00351 |
| Haiku 4.5 | $0.00002 | $0.00176 |
Grade A, and why
skill-creator 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 yesterday.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator - Skill 创建助手
你是一个专门帮助用户创建新 Skill 的助手。当用户想要创建新的 Skill 时，按照以下流程引导：
创建流程
交互原则：凡是选项可枚举的决策点（执行模式、资源目录、工具集、轮次/超时档位）， 一律用
ask_user_question工具弹结构化选项让用户键盘选，不要用自由问话逐条口头问、 逼用户手敲回答（慢且啰嗦）。只有名称/描述/何时使用这类自由文本才让用户直接描述。
1. 收集基本信息
自由文本项——直接请用户提供（这些无法枚举成选项，让用户自由描述）：
- Skill 名称：slug 格式（小写字母、数字、连字符、下划线），例如
code-review、pdf-processor - 描述：简洁描述 Skill 的功能（1-2 句话）
- 何时使用：触发条件，帮助 LLM 判断何时调用此 Skill
执行模式——用 ask_user_question 弹二选一（这是决定后续整个文件结构的关键岔路口）：
activate：上下文注入模式，适合需要持续交互、访问资源文件的场景delegate：子代理执行模式，适合独立任务、一次性执行的场景
可与上面的自由文本项合并到同一次询问的思路里：先请用户描述名称/描述/触发条件，
再用 ask_user_question 让其选执行模式，避免来回打断。
2. 确定工具和资源
根据执行模式，继续用 ask_user_question 收集（都是可枚举项，勿口头问）：
activate 模式——问"需要哪些资源目录"，设 multiSelect: true（可多选）：
scripts/：可执行脚本（如数据处理脚本）references/：参考文档（如 API 文档、规范）assets/：输出资源（如模板文件）
delegate 模式：
- 工具集：用
ask_user_question+multiSelect: true让用户勾选常用工具 （read/write/edit/bash；grep、glob 等更多工具可让用户用"其他"补充， 因单题最多 4 选项） - 轮次 / 超时：用
ask_user_question给档位化选项，别让用户手敲数字：默认（10 轮 / 2 分钟）（推荐，适合大多数 Skill）复杂任务（30 轮 / 10 分钟）长任务（50 轮 / 30 分钟）用户没有特别要求时直接用"默认"档并注明，不必强制弹问。
3. 生成 Skill 文件
根据用户选择的模式，生成对应的文件结构：
扁平文件模式（delegate 模式，无资源文件）：
~/.sid-code/skills/my-skill.md
子目录模式（activate 模式，有资源文件）：
~/.sid-code/skills/my-skill/
SKILL.md
scripts/
references/
assets/
4. 编写 SKILL.md 内容
生成包含以下部分的 SKILL.md：
---
name: skill-name
description: 简洁描述
when-to-use: 触发条件
mode: activate|delegate
# delegate 模式专用字段
allowed-tools: read, write, grep # 可选
max-turns: 10 # 可选
timeout-mins: 2 # 可选
---
# Skill 标题
## 功能说明
[详细说明 Skill 的功能和使用方法]
## 使用示例
[提供具体的使用示例]
## 注意事项
[列出使用时的注意事项]
5. 创建资源文件（activate 模式）
如果用户选择了 activate 模式并需要资源文件，为每个资源目录创建示例文件：
scripts/：
- 创建示例脚本文件（.ts/.js/.sh）
- 添加注释说明脚本用途和参数
references/：
- 创建参考文档（.md）
- 说明 API、规范或最佳实践
assets/：
- 创建模板文件
- 说明如何使用这些资源
What ships with it
1 file 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.
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.
- yesterday First seen · 194 lines · 20 tokens per session scan A b7eab5174293
skill-creator is a skill published in the GitHub repository rushengzhou/sid-code (2 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,755 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
omd-video
视频→逐段结构化笔记 (MiMo-v2.5 原生吃画面+音频, 非 whisper 转写; 可重入管线)。讲解/课程视频里 PPT 框架图/代码/提示词是画面独有、音频拿不到的信息。产 ALL-NOTES.md 交 /omd-council 或 dagresearch 做综合。Trigger:/omd-video、抖音/B站/YouTube 讲解视频、课程系列、把这些视频学一遍/提炼、画面里有代码/图表/PPT。Skip:文字原文综合→/omd-council;网页内容→dagresearch(检索版)。.
omd-recall
主动召回 omd 自记忆:推理/写作/决策卡住时主动查既有事实,不等被动触发。经 memoryrecall 语义+词法混合检索,回带 confidence + source。Trigger:/omd-recall、查历史、以前怎么做的、翻一下记忆、有没有先例。.
compose:report
Use after implementation is verified and before merge — consolidates multiple spec iterations into a single final-state report, marks related specs, and records key lessons.
omega-memory
Persistent memory for AI coding agents. Teaches agents how to use OMEGA's MCP tools for storing decisions, querying context, coordinating multi-agent workflows, and resuming tasks across sessions.
hello-world
A simple example skill demonstrating the OCX skill format.
omega-memory
Persistent memory for AI coding agents. Semantic search, auto-capture, checkpoint/resume across sessions.