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 commands/sumulige/sumulige-claude/skill-creategit clone --depth 1 https://github.com/sumulige/sumulige-claudeWrote 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/commands/sumulige/sumulige-claude/skill-create)<a href="https://agentmods.dev/commands/sumulige/sumulige-claude/skill-create"><img src="https://agentmods.dev/badge/commands/sumulige/sumulige-claude/skill-create.svg" alt="Measured on agentmods" 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 | $0.00006 | $0.00567 |
| Opus 5 | $0.00003 | $0.00283 |
| Sonnet 5 | $0.00001 | $0.00113 |
| Haiku 4.5 | $0.00001 | $0.00057 |
Grade A, and why
skill-create 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 3d 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
Create a new skill using the standard template.
Step 1: Get Skill Information
Ask the user for:
- Skill name (kebab-case, e.g.,
code-reviewer) - Description (one-line summary)
- Category (development, design, analysis, workflow, etc.)
- Difficulty (beginner, intermediate, advanced)
Step 2: Create Skill Directory
Create the skill directory structure:
mkdir -p .claude/skills/{skill-name}/{templates,examples}
Step 3: Generate SKILL.md
Use this template:
# {Skill Name}
> {Description}
**版本**: 1.0.0
**作者**: AI
**标签**: [{category}]
**难度**: {difficulty}
---
## 概述
{Detailed description of what this skill does}
## 适用场景
- {Scenario 1}
- {Scenario 2}
- {Scenario 3}
## 触发关键词
{trigger keywords}
## 使用方法
### 基础用法
{Example usage}
## 输出格式
{Output format description}
## 注意事项
- {Note 1}
- {Note 2}
## 相关技能
- [Related Skill](../related-skill/)
## 更新日志
### 1.0.0 ({current-date})
- 初始版本
Step 4: Generate metadata.yaml
name: {skill-name}
version: 1.0.0
author: AI
description: {description}
tags:
- {category}
triggers:
- {trigger1}
- {trigger2}
dependencies: []
difficulty: {difficulty}
Step 5: Add to RAG Index
Update .claude/rag/skill-index.json:
{
"skills": [
{
"name": "{skill-name}",
"description": "{description}",
"keywords": ["{trigger1}", "{trigger2}"],
"path": ".claude/skills/{skill-name}/SKILL.md"
}
]
}
Step 6: Verify
Confirm with user:
- Skill created at
.claude/skills/{skill-name}/ - Added to RAG index
- Ready to use
Example
User: "Create a skill called api-tester for testing REST APIs"
→ Create .claude/skills/api-tester/ with:
- SKILL.md (filled with API testing content)
- metadata.yaml
- templates/request.md
- examples/basic-test.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.
- 3d ago First seen · 132 lines · 6 tokens per session scan A bb5b44320c0f
skill-create is a command published in the GitHub repository sumulige/sumulige-claude (2 stars, last pushed 6mo ago), licensed MIT. It adds 6 tokens to every session and 567 once invoked, about $0.0000 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 commands, from other repositories
doctor
Run read-only health checks on the Kobiton automate plugin (CLI, credentials, profile).
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
handoff
Force a session catchup or a memory promotion outside the hook lifecycle. Default is catchup (read-only); promote is HITL gated.
gate
You are the Gate System controller. Execute quality gate reviews based on the user's request.