python-tool-builder

python-tool-builder is a skill for Claude Code, Codex from Limbicnation/hermes-asset-pipeline. It costs 44 tokens per session (881 once invoked), scanned A, original, Apache-2.0.

A template and maintenance workflow for building custom Python tools for the ComfyUI–Blender–Godot pipeline. Python is a programming language; the workflow uses uv to create isolated environments and manage dependencies.

In plain words
What is it for?
Use it to scaffold Python tools, create one virtual environment per tool, add and lock dependencies with uv, and organize source code, tests, and project metadata.
Why use it?
It keeps each tool’s packages separate and records the versions needed to reproduce its setup. This reduces dependency conflicts and undocumented installation steps.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for hermes-agent. Also seen: built for hermes-agent.

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 skills/limbicnation/hermes-asset-pipeline/python-tool-builder
Any agent
npx skills add Limbicnation/hermes-asset-pipeline --skill python-tool-builder
Clone the repo
git clone --depth 1 https://github.com/Limbicnation/hermes-asset-pipeline

Made for: Claude Code, Codex.

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 python-tool-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/limbicnation/hermes-asset-pipeline/python-tool-builder.svg)](https://agentmods.dev/skills/limbicnation/hermes-asset-pipeline/python-tool-builder)
Your own site
<a href="https://agentmods.dev/skills/limbicnation/hermes-asset-pipeline/python-tool-builder"><img src="https://agentmods.dev/badge/skills/limbicnation/hermes-asset-pipeline/python-tool-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 881 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 5.1 $0.00044 $0.00881
Opus 5 $0.00022 $0.00441
Sonnet 5 $0.00009 $0.00176
Haiku 4.5 $0.00004 $0.00088

Measured 6d ago against content hash 77e974fa83a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

python-tool-builder 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 6d 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.

pipeline/python-tool-builder/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Python Tool Builder Skill

Scaffold and maintain Python tools for the pipeline with proper isolation and dependency management.

Project Scaffolding

# Create new tool in pipeline/lib/
cd pipeline/lib
uv init --name $TOOL_NAME
uv add requests Pillow watchdog numpy

# Structure:
# pipeline/lib/$TOOL_NAME/
# ├── pyproject.toml        ← uv managed
# ├── src/$TOOL_NAME/
# │   ├── __init__.py
# │   ├── main.py
# │   └── utils.py
# ├── tests/
# │   └── test_main.py
# └── README.md

Dependency Management Rules

  1. Always use uv — never pip install directly into system Python
  2. One venv per toolpipeline/lib/$TOOL_NAME/.venv
  3. Pin versions in CIuv pip freeze > requirements.lock
  4. No stray dependencies — if it's not in pyproject.toml, it's not installed

Virtual Environment Workflow

# Activate venv
source pipeline/lib/$TOOL_NAME/.venv/bin/activate

# Run tool
python -m $TOOL_NAME

# Update dependencies
uv add newpackage
uv sync

# Lock versions (for reproducibility)
uv pip freeze | grep -v "#" > pipeline/lib/$TOOL_NAME/requirements.lock

Pipeline-Specific Tool Template

#!/usr/bin/env python3
"""
$TEMPLATE_TOOL_NAME — one-line description.
Run: python -m $TEMPLATE_TOOL_NAME [args]
"""
import argparse
import os
import sys
from pathlib import Path

# Ensure project root in path
ROOT = Path(__file__).parent.parent.parent.parent
sys.path.insert(0, str(ROOT / "lib" / "$TEMPLATE_TOOL_NAME" / "src"))

def main():
    parser = argparse.ArgumentParser(description="$TEMPLATE_TOOL_NAME")
    parser.add_argument("--input", type=Path, required=True)
    parser.add_argument("--output", type=Path, default=None)
    args = parser.parse_args()
    
    output = args.output or args.input.with_suffix(".out.png")
    # TODO: implement transformation
    print(f"Processed: {args.input} → {output}")

if __name__ == "__main__":
    main()

Running in the Pipeline venv

The main pipeline venv at awesome-hermes-agent/.venv has:

  • Pillow, opencv-python, numpy, watchdog, requests, h5py, trimesh
  • pydantic, fastapi, uvicorn

Read the full file on GitHub · 122 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. 6d ago First seen · 122 lines · 44 tokens per session scan A 77e974fa83a2

Subscribe to this mod's changes

python-tool-builder is a skill published in the GitHub repository Limbicnation/hermes-asset-pipeline (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 881 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 skills, from other repositories

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

typing-exclusion-worker

Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.

getsentry/skills · 57 tokens

python

Python development with ruff, mypy, pytest - TDD and type safety.

alinaqi/maggy · 18 tokens

splitting-oversized-modules

Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…

PostHog/posthog · 197 tokens