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/warroom-ceo/core/example-skillnpx skills add WARROOM-CEO/CORE --skill example-skillgit clone --depth 1 https://github.com/WARROOM-CEO/COREWhat 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 | $0.00067 | $0.00703 |
| Opus 5 | $0.00034 | $0.00351 |
| Sonnet 5 | $0.00013 | $0.00141 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
example-skill-th-th 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language: All user-facing output — explanations, summaries, and any text the user will read — must be written in Thai (ภาษาไทย). Internal logic, file paths, code snippets, and technical values remain in English.
Example Skill — Thai Edition
This skill demonstrates the structure and format for Claude Code plugin skills.
Overview
Skills are model-invoked capabilities that Claude autonomously uses based on task context. Unlike commands (user-invoked) or agents (spawned by Claude), skills provide contextual guidance that Claude incorporates into its responses.
When This Skill Applies
This skill activates when the user's request involves:
- Creating or understanding plugin skills
- Skill template or reference needs
- Skill development patterns
Skill Structure
Required Files
skills/
└── skill-name/
└── SKILL.md # Main skill definition (required)
Optional Supporting Files
skills/
└── skill-name/
├── SKILL.md # Main skill definition (English + Thai for user-facing parts)
├── SKILL-TH.md # Full Thai translation for users to read
├── README.md # Additional documentation
├── references/ # Reference materials
│ └── patterns.md
├── examples/ # Example files
│ └── sample.md
└── scripts/ # Helper scripts
└── helper.sh
Frontmatter Options
Skills support these frontmatter fields:
- name (required): Skill identifier — append
-thsuffix to distinguish from official skills - description (required): Trigger conditions — include both Thai and English phrases for broader activation
- version (optional): Semantic version number
- license (optional): License information or reference
Writing Effective Descriptions
The description field is crucial - it tells Claude when to invoke the skill.
Good description patterns:
description: This skill should be used when the user asks to "specific phrase", "another phrase", mentions "keyword", or discusses topic-area.
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.
- 2d ago First seen · 89 lines · 67 tokens per session scan A 386a850eac95
example-skill-th-th is a skill published in the GitHub repository WARROOM-CEO/CORE (30 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 703 once invoked, about $0.0003 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
agent-skill-builder
Quickly creates new Claude Code skills or translates ChatGPT projects into Claude Code skills. Handles skill scaffolding, frontmatter, directory structure, and ChatGPT-to-Claude migration. Use when the user wants to 'create a skill,' 'make a new slash command,' 'convert a ChatGPT project,' 'translate a GPT to Claude,'…
mcp2agy-reporter-agent
Reporter subagent definition for the mcp2agy pipeline. This agent translates verified findings into publication-ready security reports and GHSA advisory drafts. Do NOT use this agent directly — it is invoked by the audit pipeline.
skill-creator
创建高效技能的指南。当用户想要创建新技能(或更新现有技能)以扩展 Claude 的能力,包括专业知识、工作流程或工具集成时,应使用此技能。.
self-assessment
全面的 Claude Code 自我评估和学习路径顾问。运行覆盖 10 个功能领域的多类别测验,生成详细的技能档案和各主题评分,识别具体差距,并生成包含优先级下一步骤的个性化学习路径。当用户说"assess my level"(评估我的水平)、"take the quiz"(参加测验)、"find my level"(查找我的级别)、"where should I start"(我应该从哪里开始)、"what should I learn next"(我接下来应该学什么)、"check my skills"(检查我的技能)、"skill check"(技能检查)或 "level up"(升级)时使用。.
slack-gif-creator
Skill "slack-gif-creator" from Fantasia1999/skills-zh, covering slack gif 创建器, slack 要求, 核心工作流程, 1. 创建构建器 and 2. 生成帧.
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…