agentmods.dev

skill_creator

skill_creator is a skill for Claude Code, Codex from Rayan55050/progressive-agent. It costs 15 tokens per session (836 once invoked), scanned A, original, MIT.

A skill for creating new assistant skills as Markdown instruction files with a defined name, description, tools, and trigger words. A skill is an extension that teaches an AI how to handle a particular kind of task.

In plain words
What is it for?
Use it to design and save new skills for tasks such as web research, file handling, email, or command-line work.
Why use it?
It provides a repeatable structure for extending the assistant instead of writing ad-hoc instructions each time. It also documents which tools the new skill can use.

Skill for Claude CodeCodex

not rated 2 6d ago A scan 15 tokens original MIT
View the source file Rayan55050/progressive-agent
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.

agentmods
npx agentmods add skills/rayan55050/progressive-agent/skill_creator
Any agent
npx skills add Rayan55050/progressive-agent --skill skill_creator
Clone the repo
git clone --depth 1 https://github.com/Rayan55050/progressive-agent

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_creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/rayan55050/progressive-agent/skill_creator.svg)](https://agentmods.dev/skills/rayan55050/progressive-agent/skill_creator)
Your own site
<a href="https://agentmods.dev/skills/rayan55050/progressive-agent/skill_creator"><img src="https://agentmods.dev/badge/skills/rayan55050/progressive-agent/skill_creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.00836
Opus 5 $0.00008 $0.00418
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00002 $0.00084

Measured 4d ago against content hash e93aa61480fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

skills/skill_creator/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator — самообучение

Ты умеешь создавать новые скиллы для себя. Это как расширение собственных возможностей.

Как создать новый скилл

  1. Создай папку и файл SKILL.md через file_write
  2. Путь: skills/{skill_name}/SKILL.md (в корне проекта)
  3. Формат — YAML frontmatter + Markdown инструкции

Шаблон SKILL.md

---
name: имя_скилла
description: "Краткое описание"
tools:
  - список_тулов_которые_нужны
trigger_keywords:
  - ключевое_слово_1
  - ключевое_слово_2
---

# Название скилла

Инструкции для себя: когда и как использовать этот скилл.

## Инструменты
Описание каждого тула и его параметров.

## Правила
Ограничения и правила использования.

Доступные тулы для новых скиллов

Тулы, которые уже зарегистрированы и которые можно использовать:

Поиск в интернете

  • web_search — быстрый поиск (query, topic, max_results)
  • web_extract — извлечение контента из URL
  • web_research — глубокий ресёрч

Файлы

  • file_search, file_read, file_list, file_write, file_delete
  • file_open, file_send, file_pdf, file_copy

Email

  • email_inbox, email_read, email_compose

CLI

  • cli_exec — выполнение команд (command, shell, working_dir)

STT

  • stt — распознавание голоса

Правила создания скиллов

  1. Имя папки = имя скилла (латиница, snake_case)
  2. trigger_keywords — минимум 3-5 ключевых слов на русском И английском
  3. tools — только из списка доступных тулов выше. Нельзя ссылаться на несуществующие
  4. Инструкции — конкретные, с примерами. Ты пишешь инструкции ДЛЯ СЕБЯ
  5. Правила — обязательно добавь секцию с ограничениями
  6. После создания — скажи владельцу, что скилл создан и будет доступен после перезапуска

Пример: создание скилла для крипты

Если владелец скажет "научись отслеживать биткоин":

  1. Создай skills/crypto/SKILL.md через file_write с:
    • tools: [web_search]
    • keywords: [биткоин, btc, крипта, курс, bitcoin]
    • Инструкции: как искать курсы, где брать данные, формат ответа

Read the full file on GitHub · 103 lines

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. 4d ago First seen · 103 lines · 15 tokens per session scan A e93aa61480fa

Subscribe to this mod's changes

skill_creator is a skill published in the GitHub repository Rayan55050/progressive-agent (2 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 836 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.

Autonomous AgentsBuilding agentsagent-frameworkagent-skillsai-agentai-agentschatbot
Related

Other skills, from other repositories

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

HKUDS/nanobot · 22 tokens

summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

HKUDS/nanobot · 32 tokens

weather

Get current weather and forecasts (no API key required).

HKUDS/nanobot · 13 tokens

github

Interact with GitHub using the gh CLI. Use gh issue, gh pr, gh run, and gh api for issues, PRs, CI runs, and advanced queries.

HKUDS/nanobot · 44 tokens

hive.browser-automation

Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…

aden-hive/hive · 142 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens