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 agents/alirezarezvani/claude-code-skill-factory/readmegit clone --depth 1 https://github.com/alirezarezvani/claude-code-skill-factoryWrote 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/agents/alirezarezvani/claude-code-skill-factory/readme)<a href="https://agentmods.dev/agents/alirezarezvani/claude-code-skill-factory/readme"><img src="https://agentmods.dev/badge/agents/alirezarezvani/claude-code-skill-factory/readme.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 | $0.00000 | $0.02262 |
| Opus 5 | $0.00000 | $0.01131 |
| Sonnet 5 | $0.00000 | $0.00452 |
| Haiku 4.5 | $0.00000 | $0.00226 |
Grade A, and why
README 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 5d 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 — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Factory Navigation Agents
Interactive guide system for building custom Skills, Prompts, and Agents using the Claude Code Skills Factory.
🎯 Navigation System Overview
Architecture: Orchestrator + 3 Specialists
User Request
↓
factory-guide (Orchestrator)
├→ skills-guide (Build Claude Skills)
├→ prompts-guide (Generate Mega-Prompts)
└→ agents-guide (Build Claude Agents)
🤖 Available Agents (4 Total)
1. factory-guide (Orchestrator) - START HERE
Purpose: Main entry point - asks what you want to build and delegates to specialists
Use when: "I want to build something" or "Help me with the skills factory"
What it does:
- Asks 1 simple question: What to build? (Skill, Prompt, or Agent)
- Delegates to appropriate specialist
- Provides final summary
Tools: Read, Grep (lightweight) Model: haiku (fast) Color: Purple (orchestration)
Invoke:
I want to build something for my project
2. skills-guide (Specialist)
Purpose: Build custom Claude Skills (multi-file capabilities)
Questions: 4-5 straightforward
- Business type/domain?
- What tasks should the skill handle?
- Need Python code or just prompts?
- How many skills to generate?
- Any special requirements?
What it generates:
- Complete skill folder (SKILL.md, Python if needed, samples)
- ZIP file for distribution
- Validation of YAML frontmatter
- Installation instructions
Tools: Read, Write, Bash, Grep, Glob (full file creation) Model: sonnet (intelligent) Color: Blue (strategic)
Example:
Help me build a skill for analyzing customer feedback
Output: generated-skills/customer-feedback-analyzer/
3. prompts-guide (Specialist)
Purpose: Generate mega-prompts using prompt-factory skill
Questions: 3-4 simple
- Preset (69 options) or Custom?
- What role? (if custom)
- Output format? (XML/Claude/ChatGPT/Gemini)
- Core or Advanced mode?
What it does:
- Guides you to use the prompt-factory skill
- Helps choose from 69 professional presets
- Explains format differences
- Shows how to use generated prompts
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.
- 5d ago First seen · 397 lines · 0 tokens per session scan A ff489fee991c
README is an agent published in the GitHub repository alirezarezvani/claude-code-skill-factory (855 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,262 tokens. 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 agents, from other repositories
proposal-critic-agent
Agent "proposal-critic-agent" from chrisblattman/claudeblattman, covering proposal critic agent, personas, catalog conflict, maintenance tax and compounder.
Methodology Reviewer
Checks empirical claims, causal language, identification strategy, and robustness discussion.
chief-of-staff
Advisor to a busy principal. Optimizes for the user's time, attention, and decision quality. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
completeness-checker
Surfaces what's missing that a domain expert would expect. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
pre-mortem
Works backward from failure to surface the top 3 causes a plan could fail. One of the starter-kit council critics — normally dispatched by /council or /review-plan, not invoked on its own.
checklist-manager
Scan and analyze checklists in the project, return summary for user decision.