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 skills add jscholz/hermes-agent-workflow --skill heartmulagit clone --depth 1 https://github.com/jscholz/hermes-agent-workflowWrote 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/skills/jscholz/hermes-agent-workflow/heartmula)<a href="https://agentmods.dev/skills/jscholz/hermes-agent-workflow/heartmula"><img src="https://agentmods.dev/badge/skills/jscholz/hermes-agent-workflow/heartmula.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 5.1 | $0.00034 | $0.01745 |
| Opus 5 | $0.00017 | $0.00873 |
| Sonnet 5 | $0.00007 | $0.00349 |
| Haiku 4.5 | $0.00003 | $0.00175 |
Grade A, and why
heartmula 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.
This is a copy
89% identical to heartmula — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HeartMuLa - Open-Source Music Generation
Overview
HeartMuLa is a family of open-source music foundation models (Apache-2.0) that generates music conditioned on lyrics and tags. Comparable to Suno for open-source. Includes:
- HeartMuLa - Music language model (3B/7B) for generation from lyrics + tags
- HeartCodec - 12.5Hz music codec for high-fidelity audio reconstruction
- HeartTranscriptor - Whisper-based lyrics transcription
- HeartCLAP - Audio-text alignment model
When to Use
- User wants to generate music/songs from text descriptions
- User wants an open-source Suno alternative
- User wants local/offline music generation
- User asks about HeartMuLa, heartlib, or AI music generation
Hardware Requirements
- Minimum: 8GB VRAM with
--lazy_load true(loads/unloads models sequentially) - Recommended: 16GB+ VRAM for comfortable single-GPU usage
- Multi-GPU: Use
--mula_device cuda:0 --codec_device cuda:1to split across GPUs - 3B model with lazy_load peaks at ~6.2GB VRAM
Installation Steps
1. Clone Repository
cd ~/ # or desired directory
git clone https://github.com/HeartMuLa/heartlib.git
cd heartlib
2. Create Virtual Environment (Python 3.10 required)
uv venv --python 3.10 .venv
. .venv/bin/activate
uv pip install -e .
3. Fix Dependency Compatibility Issues
IMPORTANT: As of Feb 2026, the pinned dependencies have conflicts with newer packages. Apply these fixes:
# Upgrade datasets (old version incompatible with current pyarrow)
uv pip install --upgrade datasets
# Upgrade transformers (needed for huggingface-hub 1.x compatibility)
uv pip install --upgrade transformers
4. Patch Source Code (Required for transformers 5.x)
Patch 1 - RoPE cache fix in src/heartlib/heartmula/modeling_heartmula.py:
In the setup_caches method of the HeartMuLa class, add RoPE reinitialization after the reset_caches try/except block and before the with device: block:
# Re-initialize RoPE caches that were skipped during meta-device loading
from torchtune.models.llama3_1._position_embeddings import Llama3ScaledRoPE
for module in self.modules():
if isinstance(module, Llama3ScaledRoPE) and not module.is_cache_built:
module.rope_init()
module.to(device)
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.
- 7d ago First seen · 171 lines · 34 tokens per session scan A f5b5d9ad6c27
heartmula is a skill published in the GitHub repository jscholz/hermes-agent-workflow (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,745 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to heartmula, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
stable-diffusion
Text-to-image generation, inpainting, and img2img.
huggingface-lora-space-builder
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers…
baoyu-danger-gemini-web
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation"…
seedance-antislop
This skill should be used when a Seedance 2.0 prompt contains generic AI filler, hollow superlatives, vague cinematic language, bloated adjectives, weak verbs, or needs sharper production-specific wording.
seedance-filter
This skill should be used when a Seedance 2.0 prompt is blocked, rejected, silently degraded, or likely to trigger a content filter; or when the user asks for a safer rewrite without losing the creative intent.
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt is slop-heavy, generic, padded with empty quality words, tripping false-positive filters, or needs precise English production vocabulary for camera, lighting, motion, VFX, audio, and constraints.