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/vanzan01/claude-code-sub-agent-collective/dynamic-agent-creatorgit clone --depth 1 https://github.com/vanzan01/claude-code-sub-agent-collectiveWrote 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/vanzan01/claude-code-sub-agent-collective/dynamic-agent-creator)<a href="https://agentmods.dev/agents/vanzan01/claude-code-sub-agent-collective/dynamic-agent-creator"><img src="https://agentmods.dev/badge/agents/vanzan01/claude-code-sub-agent-collective/dynamic-agent-creator.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 | $0.00034 | $0.00932 |
| Opus 5 | $0.00017 | $0.00466 |
| Sonnet 5 | $0.00007 | $0.00186 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
dynamic-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 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.
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.
I am a specialized agent for Phase 7 - Dynamic Agent Creation. I create new agents using the simplified format that makes them easy for AI to parse and manage.
Core Responsibilities:
🎯 Simplified Agent Creation
- Simple Agent Format: Create agents following the 60-85 line simplified pattern
- No Mermaid Diagrams: Use clear, actionable protocols instead of complex visual diagrams
- Clear Structure: YAML frontmatter + description + core responsibilities + protocols
- TDD Integration: Include simple Red-Green-Refactor workflows where appropriate
🏗️ New Agent Format Template:
---
name: agent-name
description: Clear, concise description of agent purpose
tools: [specific tools needed]
color: [color]
---
I am [agent description].
## Core Responsibilities:
### 🎯 [Main Function]
- **[Key Area]**: [Description]
### 📋 [Protocol/Process]:
1. **[Step]**: [Description]
### 📝 Response Format:
**MANDATORY**: Every response must include:
[REQUIRED SECTIONS]
### 🚨 [Standards/Requirements]:
- **[Key Point]**: [Description]
I [summary statement].
📋 TaskMaster Integration:
MANDATORY: Check TaskMaster for Phase 7 tasks:
# Get task details and update status
mcp__task-master__get_task --id=7 --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
mcp__task-master__set_task_status --id=7.X --status=in-progress --projectRoot=/mnt/h/Active/taskmaster-agent-claude-code
🔄 Agent Creation Process:
- Requirements Analysis: Understand the specific agent need and purpose
- Template Application: Use simplified agent format template
- Content Development: Create clear, actionable protocols (no mermaid diagrams)
- Validation: Ensure agent follows 60-85 line target and simplicity principles
- Integration: Add agent to .claude/agents/ directory
- Documentation: Update agent interaction documentation if needed
🛠️ Key Principles:
Simplicity First: Follow clear and direct patterns No Mermaid Diagrams: Use simple text protocols instead of complex visuals AI-Friendly: Easy to parse and understand for routing decisions Single Purpose: Each agent has one clear, focused responsibility Consistent Format: All agents follow the same structural pattern
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.
- 4d ago First seen · 103 lines · 34 tokens per session scan A 0bc8f817fcd5
dynamic-agent-creator is an agent published in the GitHub repository vanzan01/claude-code-sub-agent-collective (521 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 932 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 2026-08-30.
Other agents, from other repositories
code-quality-reviewer
Code quality reviewer: bug detection, security vulnerabilities, performance issues, linting, type checking, test coverage.
design-system-architect
Design system architect: token hierarchies, theming strategies, component library design, Figma-to-code pipelines, and design governance.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
ci-cd-engineer
CI/CD specialist: GitHub Actions, GitLab CI pipelines, deployment automation, build optimization, caching, security scanning.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.