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 skills add tswicegood/claude-skills --skill agent-creatorgit clone --depth 1 https://github.com/tswicegood/claude-skillsWrote 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/tswicegood/claude-skills/agent-creator)<a href="https://agentmods.dev/skills/tswicegood/claude-skills/agent-creator"><img src="https://agentmods.dev/badge/skills/tswicegood/claude-skills/agent-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tswicegood/claude-skills/agent-creator"><img src="https://agentmods.dev/badge/skills/tswicegood/claude-skills/agent-creator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.01743 |
| Opus 5 | $0.00039 | $0.00872 |
| Sonnet 5 | $0.00016 | $0.00349 |
| Haiku 4.5 | $0.00008 | $0.00174 |
Grade A, and why
agent-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 10d 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Creator for Claude Code
Create specialized Claude Code agents through an interactive interview process. Generates complete CLAUDE.md configurations with workflows, constraints, and quality gates tailored to specific roles.
Interview Process
Follow this 7-phase interview to gather requirements, then generate a complete agent configuration:
Phase 1: Role & Purpose (2-3 questions)
Goal: Understand the agent's identity and primary purpose.
Questions:
- "What would you like this agent to do? Describe the main role in a sentence or two."
- "What problem are you trying to solve with this agent?"
- "How would you name this agent role?" (e.g., 'Code Reviewer', 'Test Engineer', 'API Guardian')
Learning: The agent's identity, purpose, and the gap it fills.
Follow-up if vague: "Can you give me an example of a task this agent would handle?"
Phase 2: Responsibilities (3-4 questions)
Goal: Define MUST do vs SHOULD do vs MUST NOT do.
Questions:
- "What are the 3-5 core duties this agent MUST perform every time?"
- "Are there secondary responsibilities it SHOULD handle when relevant?"
- "What is explicitly outside this agent's scope? What should it NOT do?"
- "Are there situations where the agent should stop and ask before proceeding?"
Learning: Clear boundaries and priorities.
Follow-up if too broad: "Let's focus on the most important duty - can you break that down into specific steps?"
Phase 3: Autonomy & Constraints (2-3 questions)
Goal: Determine autonomy level and risk tolerance.
Questions:
- "How much autonomy should this agent have?"
- High: Makes decisions and implements independently
- Medium: Proposes plan, gets approval, then implements
- Low: Only analyzes and advises, never modifies
- "What mistakes would be unacceptable for this agent to make?"
- "Are there specific files, directories, or systems the agent should never touch?"
Learning: Risk tolerance and guardrails.
What ships with it
3 files 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.
- 10d ago First seen · 213 lines · 79 tokens per session scan A b451ee5a6fd1
agent-creator is a skill published in the GitHub repository tswicegood/claude-skills (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,743 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…