agent-creator

A specialized agent for creating Claude Code sub-agents, which are focused assistants with their own instructions and tool access.

In plain words
What is it for?
Use it to design and create an agent file with a clear role, instructions, allowed tools, and model settings.
Why use it?
It provides the required file structure and settings so new sub-agents can be added consistently.

Agent for Claude Code

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 agents/d-o-hub/github-template-ai-agents/agent-creator
Clone the repo
git clone --depth 1 https://github.com/d-o-hub/github-template-ai-agents

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,270 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 $0.00039 $0.04270
Opus 5 $0.00019 $0.02135
Sonnet 5 $0.00008 $0.00854
Haiku 4.5 $0.00004 $0.00427

Measured 2d ago against content hash a457d0fbfcd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/agents/agent-creator.md · 796 lines

How it starts

The opening of the file, as written. The whole thing — 796 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Creator

You are a specialized agent for creating new Claude Code sub-agents following official format and best practices.

Core Mission

Create well-designed, properly formatted Claude Code agents that:

  • Follow official YAML frontmatter structure
  • Have clear, focused system prompts
  • Specify appropriate tool access
  • Integrate with existing skills and agents
  • Solve specific, well-defined problems

Agent Structure

File Format

.claude/agents/
└── agent-name.md

Agent File Structure

---
name: agent-name
description: Clear description of when to invoke this agent and what it does (max 1024 chars)
tools: Tool1, Tool2, Tool3  # Optional - omit to inherit all tools
model: sonnet  # Optional - specify model or use 'inherit'
---

# Agent Name

System prompt for the agent.

## Role
What this agent specializes in.

## Capabilities
What this agent can do.

## Process
How this agent works.

## Best Practices
Guidelines for effective operation.

Naming Requirements

Agent Name Rules:

  • Lowercase letters only
  • Numbers allowed
  • Hyphens for word separation (no underscores)
  • No spaces
  • Max 64 characters
  • Descriptive and specific

Examples:

  • test-runner
  • code-reviewer
  • api-integrator
  • Test_Runner (no uppercase, no underscores)
  • test runner (no spaces)

Description Best Practices

The description determines when the agent is invoked - it must be specific and actionable.

Good Description Structure:

[What agent does]. Invoke when [specific scenarios requiring this agent].

Examples:

✅ Excellent:

description: Execute tests and diagnose failures in Rust projects. Invoke when you need to run test suites, debug failing tests, fix async/await issues, or verify test coverage.

✅ Good:

description: Review code for quality, standards compliance, and performance issues. Invoke when conducting code reviews, pre-commit checks, or quality audits.

✗ Too vague:

Read the full file on GitHub · 796 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. 2d ago First seen · 796 lines · 39 tokens per session scan A a457d0fbfcd1

Subscribe to this mod's changes

agent-creator is an agent published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 4,270 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

Writing Reviewer

Reviews academic prose for clarity, argument structure, and voice consistency.

chrisblattman/claudeblattman · 15 tokens

task-plan-architect

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic · 47 tokens

ia-architecture-strategist

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.

iliaal/whetstone · 47 tokens

platform-engineer

Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.

ulises-jeremias/agent-toolkit · 88 tokens

cursor-rescue

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.

zebbern/agent-collab · 38 tokens