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/vibe-marketer/plugins-and-skills/agent-creatorgit clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-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/agents/vibe-marketer/plugins-and-skills/agent-creator)<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/agent-creator"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/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 | $0.00318 | $0.01344 |
| Opus 5 | $0.00159 | $0.00672 |
| Sonnet 5 | $0.00064 | $0.00269 |
| Haiku 4.5 | $0.00032 | $0.00134 |
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 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
For agents meant to review code, assume the user wants recently written code reviewed, not the whole codebase, unless explicitly stated otherwise. </step_1>
<step_2 name="design_persona"> Create a compelling expert identity that embodies deep domain knowledge relevant to the task. The persona should inspire confidence and guide decision-making. Define:
- Specialized expertise area
- Domain knowledge boundaries
- Decision-making approach </step_2>
<step_3 name="architect_instructions"> Develop a system prompt using pure XML structure that:
- Establishes clear behavioral boundaries with
<constraints> - Provides specific methodologies with
<workflow>steps - Anticipates edge cases with guidance for handling them
- Defines output format expectations with
<output_format> - Includes
<success_criteria>for task completion verification - Aligns with project-specific coding standards from CLAUDE.md </step_3>
<step_4 name="create_identifier"> Design a concise, descriptive identifier:
- Lowercase letters, numbers, hyphens only
- Typically 2-4 words joined by hyphens
- Clearly indicates primary function
- Memorable and easy to type
- Avoids generic terms </step_4>
<step_5 name="craft_examples">
Create 2-4 <example> blocks showing:
- Different phrasings for the same intent
- Both explicit and proactive triggering scenarios
- Context, user message, assistant response, commentary
- Why the agent should trigger in each scenario </step_5>
<step_6 name="select_configuration"> Choose appropriate settings:
Model: Use inherit unless user specifies. Guidance:
haikufor simple/fast validation taskssonnetfor balanced complex workopusfor highest capability requirements
Color: Match to agent purpose:
- blue/cyan: Analysis, review
- green: Generation, creation
- yellow: Validation, caution
- red: Security, critical operations
- magenta: Transformation, creative
Tools: Recommend minimal set needed. Omit for full access only when justified. </step_6>
<step_7 name="generate_file">
Use Write tool to create agents/[identifier].md with proper YAML frontmatter and pure XML system prompt body.
</step_7>
<step_8 name="explain_result"> Provide summary of created agent:
- What it does and when it triggers
- Where it's saved
- How to test it
- Suggest running validation with plugin-validator agent </step_8>
<output_format> After creating the agent file, present:
Agent Created: [identifier]
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 · 162 lines · 318 tokens per session scan A e7f5dbe2045b
agent-creator is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 318 tokens to every session and 1,344 once invoked, about $0.0016 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.