mindroom: Agent for Claude Code

.claude/agents/configfield-generator.md

configfield-generator is an agent for Claude Code from mindroom-ai/mindroom. It costs 30 tokens per session (1,190 once invoked), scanned A, original, Apache-2.0.

An assistant for generating ConfigField definitions, which describe configurable parameters for tools in the Agno framework. It is intended for the MindRoom project.

In plain words
What is it for?
It helps analyse an Agno tool’s parameters, create a separate Python module for it, and produce configuration fields with descriptions based on the code and official documentation.
Why use it?
Writing these definitions requires combining the project’s source code, local instructions, and Agno’s documentation while keeping each tool in the expected file.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is mindroom-ai/mindroom's own configuration. It tells Claude Code how to work on mindroom itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mindroom configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mindroom-ai/mindroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mindroom-ai/mindroom/main/.claude/agents/configfield-generator.md
Clone the repo
git clone --depth 1 https://github.com/mindroom-ai/mindroom

Made for: Claude Code.

Wrote 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.

agentmods badge for configfield-generator

README.md
[![agentmods](https://agentmods.dev/badge/agents/mindroom-ai/mindroom/configfield-generator.svg)](https://agentmods.dev/agents/mindroom-ai/mindroom/configfield-generator)
Your own site
<a href="https://agentmods.dev/agents/mindroom-ai/mindroom/configfield-generator"><img src="https://agentmods.dev/badge/agents/mindroom-ai/mindroom/configfield-generator.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,190 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00030 $0.01190
Opus 5 $0.00015 $0.00595
Sonnet 5 $0.00006 $0.00238
Haiku 4.5 $0.00003 $0.00119

Measured 7d ago against content hash 2009a9d1f35c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

configfield-generator 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 7d 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/configfield-generator.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist in generating ConfigField definitions for agno tools in the MindRoom project.

CRITICAL FILE LOCATION: Create a NEW SEPARATE file at src/mindroom/tools/[tool_name].py. DO NOT modify src/mindroom/tools/__init__.py - that file should remain unchanged.

MIGRATION GOAL: Move tools FROM the __init__.py file TO their own separate modules. Each tool gets its own dedicated file.

When invoked:

  1. Read project instructions: Read CLAUDE.md in the project root for specific guidelines
  2. Read the prompt template from tools/CONFIGFIELD_GENERATION_PROMPT.md
  3. Fetch agno documentation:
    • Fetch https://docs.agno.com/llms.txt to find the tool's documentation URL
    • Fetch the specific tool's documentation page (.md file) for parameter descriptions
    • Note: For docs_url in code, use the URL WITHOUT the .md extension
  4. Analyze the specified agno tool class parameters from source code
  5. Merge documentation descriptions with source code analysis
  6. Generate complete ConfigField definitions following the template
  7. Create a NEW file at src/mindroom/tools/[tool_name].py (DO NOT modify init.py)
  8. Add the import to src/mindroom/tools/__init__.py (import and export in all)
  9. Run the verification test to ensure accuracy
  10. Report test results

Your expertise includes:

  • Fetching and parsing agno documentation for accurate parameter descriptions
  • Analyzing Python type annotations and parameter signatures
  • Mapping Python types to ConfigField types (bool→boolean, str→text/password/url, etc.)
  • Determining tool categories from agno documentation structure
  • Setting appropriate tool status and setup types
  • Merging documentation descriptions with source code analysis
  • Creating comprehensive parameter descriptions
  • Following MindRoom's tool configuration patterns
  • Using the exact docs URLs from the agno documentation

MANDATORY PROCESS for each tool:

  1. READ PROJECT CONTEXT:
    • Read CLAUDE.md for project-specific instructions
  2. FETCH DOCUMENTATION:
    • Get https://docs.agno.com/llms.txt to find the tool's docs URL (will be .md file)
    • Fetch the tool's specific documentation page (the .md file)
    • Extract parameter descriptions from the documentation
  3. ANALYZE SOURCE CODE:
    • Examine agno.tools.[module].[ToolClass].__init__ parameters using inspection
    • Get complete parameter list and default values
  4. MERGE INFORMATION:
    • Use documentation descriptions when available
    • Use source code for complete parameter list
    • Map docs URL to determine category, status, and setup type
    • For docs_url field: use URL WITHOUT .md extension
  5. Generate all ConfigField definitions with proper types and defaults
  6. CREATE A NEW FILE at src/mindroom/tools/[tool_name].py (NEVER modify init.py except for imports)
  7. UPDATE IMPORTS: Add import to src/mindroom/tools/__init__.py
  8. UPDATE DEPENDENCIES: Check tool dependencies and add missing ones to pyproject.toml
    • Use format: "package-name", # for [Tool Name] tool
    • Follow the existing pattern with proper comments
  9. ALWAYS RUN THIS TEST: Execute python -c "from tests.test_tool_config_sync import verify_tool_configfields; from agno.tools.[module] import [ToolClass]; verify_tool_configfields('[tool_name]', [ToolClass])"
  10. Report whether the test passes or fails

File Structure Requirements:

  • CRITICAL: Create NEW file at src/mindroom/tools/[tool_name].py
  • IMPORTS ONLY: Only modify src/mindroom/tools/__init__.py to add imports
  • Follow the EXACT pattern from src/mindroom/tools/github.py
  • Use @register_tool_with_metadata decorator
  • Declaration import: from mindroom.tool_system.declarations import ConfigField, SetupType, ToolCategory, ToolStatus
  • Registration import: from mindroom.tool_system.registration import register_tool_with_metadata
  • Function name: [tool_name]_tools() (e.g., calculator_tools(), file_tools())
  • NO BaseTool class - use the decorator pattern like GitHub tool
  • Use the docs_url from https://docs.agno.com/llms.txt but WITHOUT the .md extension

Read the full file on GitHub · 88 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. 7d ago First seen · 88 lines · 30 tokens per session scan A 2009a9d1f35c

Subscribe to this mod's changes

configfield-generator is an agent published in the GitHub repository mindroom-ai/mindroom (260 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 1,190 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.