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/soulcynics404/agentforge/skill-buildernpx skills add Soulcynics404/AgentForge --skill skill-buildergit clone --depth 1 https://github.com/Soulcynics404/AgentForgeWrote 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/skills/soulcynics404/agentforge/skill-builder)<a href="https://agentmods.dev/skills/soulcynics404/agentforge/skill-builder"><img src="https://agentmods.dev/badge/skills/soulcynics404/agentforge/skill-builder.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 | $0.00046 | $0.05325 |
| Opus 5 | $0.00023 | $0.02662 |
| Sonnet 5 | $0.00009 | $0.01065 |
| Haiku 4.5 | $0.00005 | $0.00532 |
Grade A, and why
Skill Builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to Skill Builder — 132 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 911 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Builder
What This Skill Does
Creates production-ready Claude Code Skills with proper YAML frontmatter, progressive disclosure architecture, and complete file$folder structure. This skill guides you through building skills that Claude can autonomously discover and use across all surfaces (Claude.ai, Claude Code, SDK, API).
Prerequisites
- Claude Code 2.0+ or Claude.ai with Skills support
- Basic understanding of Markdown and YAML
- Text editor or IDE
Quick Start
Creating Your First Skill
# 1. Create skill directory (MUST be at top level, NOT in subdirectories!)
mkdir -p ~/.claude$skills$my-first-skill
# 2. Create SKILL.md with proper format
cat > ~/.claude$skills$my-first-skill/SKILL.md << 'EOF'
---
name: "My First Skill"
description: "Brief description of what this skill does and when Claude should use it. Maximum 1024 characters."
---
# My First Skill
## What This Skill Does
[Your instructions here]
## Quick Start
[Basic usage]
EOF
# 3. Verify skill is detected
# Restart Claude Code or refresh Claude.ai
Complete Specification
📋 YAML Frontmatter (REQUIRED)
Every SKILL.md must start with YAML frontmatter containing exactly two required fields:
---
name: "Skill Name" # REQUIRED: Max 64 chars
description: "What this skill does # REQUIRED: Max 1024 chars
and when Claude should use it." # Include BOTH what & when
---
Field Requirements
name (REQUIRED):
- Type: String
- Max Length: 64 characters
- Format: Human-friendly display name
- Usage: Shown in skill lists, UI, and loaded into Claude's system prompt
- Best Practice: Use Title Case, be concise and descriptive
- Examples:
- ✅ "API Documentation Generator"
- ✅ "React Component Builder"
- ✅ "Database Schema Designer"
- ❌ "skill-1" (not descriptive)
- ❌ "This is a very long skill name that exceeds sixty-four characters" (too long)
description (REQUIRED):
- Type: String
- Max Length: 1024 characters
- Format: Plain text or minimal markdown
- Content: MUST include:
- What the skill does (functionality)
- When Claude should invoke it (trigger conditions)
- Usage: Loaded into Claude's system prompt for autonomous matching
- Best Practice: Front-load key trigger words, be specific about use cases
- Examples:
- ✅ "Generate OpenAPI 3.0 documentation from Express.js routes. Use when creating API docs, documenting endpoints, or building API specifications."
- ✅ "Create React functional components with TypeScript, hooks, and tests. Use when scaffolding new components or converting class components."
- ❌ "A comprehensive guide to API documentation" (no "when" clause)
- ❌ "Documentation tool" (too vague)
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 · 911 lines · 46 tokens per session scan A eee6e7317a1b
Skill Builder is a skill published in the GitHub repository Soulcynics404/AgentForge (1 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 5,325 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to Skill Builder, differing in 132 lines, and is treated as a copy.
Other skills, from other repositories
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.
testing-skill
Record, rewrite, and debug VCR cassettes for HTTP recordings. Use when running tests with --record-mode, verifying cassette playback, or inspecting request/response bodies in YAML cassettes.
adding-a-provider-api-feature
Add a new provider API capability (prompt caching, strict/structured tool calling, thinking/reasoning effort, service tier, safety settings, logprobs, etc.) to Pydantic AI. Use when wiring a provider feature through the library — it enforces reasoning from the existing cross-provider abstraction before designing…
migrating-langchain-to-pydantic-ai
Migrate Python LangChain or LangGraph applications to Pydantic AI. Use for LangChain agents, chains, LCEL, or direct LangGraph graphs, persistence, interrupts, and streaming. Do not use for migrations centered on createdeepagent or Deep Agents harness features.
address-feedback
Find and address unresolved PR review comments for the current branch, then continue the canonical push, reply, reaction, and resolution workflow.