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.
git clone --depth 1 https://github.com/AlexFischman/mcp-skill-creator-agencyWrote 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/commands/alexfischman/mcp-skill-creator-agency/productize)<a href="https://agentmods.dev/commands/alexfischman/mcp-skill-creator-agency/productize"><img src="https://agentmods.dev/badge/commands/alexfischman/mcp-skill-creator-agency/productize/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/commands/alexfischman/mcp-skill-creator-agency/productize"><img src="https://agentmods.dev/badge/commands/alexfischman/mcp-skill-creator-agency/productize.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 | $0.00000 | $0.01419 |
| Opus 5 | $0.00000 | $0.00709 |
| Sonnet 5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
productize 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 11d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Productization Task
Your task is to productize an AI agent in the current repository by turning it into a reusable template. Essentially, the user wants you to ensure that he can easily customize this agent for different clients.
Step-by-Step Process
- Fetch the documentation for how to create onboarding forms for AI agents with our framework: https://agency-swarm.ai/platform/marketplace/onboarding Make sure to fetch the entire page.
- Explore the current repository to understand the structure of the current agency to productize. Focus primarily on insturctions files of each agent and the shared_instructions.md file.
- Ask the user what he would like to customize accross different clients for this agent. For example, agent name, business overview, model, output format, additional notes, etc.
- Based on the user's answers, create a new OnboardingTool for an agent, as described in documentation. Example is provided below.
- Important: When converting the agent to use an OnboardingTool, make sure to preserve existing values from the repository.
- For each value (for example, business overview or server addresses) that you want to turn into a customizable field, do NOT overwrite or delete the user’s current data.
- Instead, create a field for this value in the OnboardingTool, and store the existing value as the default in
onboarding_config.py. - Place code that loads these defaults inside the
if __name__ == "__main__"block of your OnboardingTool script. - This approach keeps the user’s current settings safe while making them configurable for future onboarding.
- Run the onboarding_tool.py file to generate the onboarding_config.py file.
- Import the onboarding_config.py file to customize the agent, as described in documentation.
Example OnboardingTool
from agency_swarm.tools import BaseTool
from pydantic import Field
from typing import Optional, Literal
import os
import json
class OnboardingTool(BaseTool):
"""
Customizes the agent based on business requirements and preferences.
Add any fields you want the user to configure during onboarding.
"""
# Basic text field example
company_name: str = Field(
"Acme Corp",
description="Your company name"
)
# Textarea field example (for longer text inputs)
company_overview: str = Field(
"A company that does amazing things.",
description="Brief overview of your company or product",
json_schema_extra={"ui:widget": "textarea"},
)
model: Literal["gpt-5", "gpt-4.1"] = Field(
"gpt-4.1",
description="Select the model to use: gpt-5 or gpt-4.1"
)
# File upload field example
knowledge_files: list[str] = Field(
[],
description="Upload documentation files for the agent to reference.",
json_schema_extra={
"x-file-upload-path": "./agent_name/files", # Replace with your agent folder. FIles will be automatically uploaded to this path.
},
)
# Add more fields as needed:
# - Use str for text inputs
# - Use Optional[str] for optional inputs
# - Use list[str] for file uploads
# - Add json_schema_extra={"ui:widget": "textarea"} for multi-line text
# - Add json_schema_extra={"ui:placeholder": "placeholder"} for field placeholder text
# - Add json_schema_extra={"x-file-upload-path": "./path"} for file uploads
def run(self):
"""Saves configuration to onboarding_config.py"""
# Get the directory where this tool is located
tool_dir = os.path.dirname(os.path.abspath(__file__))
config_path = os.path.join(tool_dir, "onboarding_config.py")
# Convert tool fields to dictionary
config = self.model_dump()
# Convert to Python code format
json_str = json.dumps(config, indent=4)
json_str = json_str.replace(': null', ': None').replace(': true', ': True').replace(': false', ': False')
python_code = f"# Auto-generated configuration\n\nconfig = {json_str}\n"
# Write to file
with open(config_path, "w", encoding="utf-8") as f:
f.write(python_code)
return f"Configuration saved to {config_path}"
# Test the tool
if __name__ == "__main__":
tool = OnboardingTool(
company_name="Test Company",
company_overview="This is a test.",
support_email="[email protected]"
)
print(tool.run())
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.
- 11d ago First seen · 169 lines · 0 tokens per session scan A 9439fbf618ff
productize is a command published in the GitHub repository AlexFischman/mcp-skill-creator-agency (2 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,419 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 2026-08-31.
Other commands, from other repositories
add-endpoint
Scaffold a new API endpoint with full layering.
review
Review code changes against project conventions.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.