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 hamzabellouch/agent-skills --skill dsp-audio-filter-effectsgit clone --depth 1 https://github.com/hamzabellouch/agent-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/skills/hamzabellouch/agent-skills/dsp-audio-filter-effects)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/dsp-audio-filter-effects"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/dsp-audio-filter-effects/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/skills/hamzabellouch/agent-skills/dsp-audio-filter-effects"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/dsp-audio-filter-effects.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 | $0.00068 | $0.01209 |
| Opus 5.5 | $0.00027 | $0.00484 |
| Sonnet 5.5 | $0.00014 | $0.00242 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
dsp-audio-filter-effects 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 18d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Digital Signal Processing (DSP) Audio Filter & Effects Skill Guide
This skill covers the design, mathematical formulation, and software implementation of digital audio filters, dynamic range compressors, and spectral transforms.
1. Filter Classifications: IIR vs FIR
+-----------------------------------+-----------------------------------+
| Infinite Impulse Response (IIR) | Finite Impulse Response (FIR) |
+-----------------------------------+-----------------------------------+
| - Feedback (Recursive) | - Feedforward only (Non-recursive)|
| - Low computational cost (CPU) | - Linear phase response available |
| - Examples: Butterworth, Biquad | - Inherently stable |
| - Ideal for real-time live audio | - Ideal for mastering & phase- |
| filters & equalizers | critical crossover filters |
+-----------------------------------+-----------------------------------+
2. Production Code Implementations
A. Butterworth Bandpass & Highpass Filters (Python / SciPy)
import numpy as np
from scipy import signal
class AudioFilterEngine:
def __init__(self, sample_rate: int = 44100):
self.sample_rate = sample_rate
def butter_bandpass(self, lowcut: float, highcut: float, order: int = 4):
nyquist = 0.5 * self.sample_rate
low = lowcut / nyquist
high = highcut / nyquist
# Return second-order sections (SOS) for numerical stability
sos = signal.butter(order, [low, high], btype="bandpass", output="sos")
return sos
def apply_filter(self, data: np.ndarray, sos: np.ndarray) -> np.ndarray:
# Applies filter forward and backward (zero-phase) or single-pass.
return signal.sosfilt(sos, data)
def compute_spectral_centroid(audio_data: np.ndarray, sample_rate: int) -> float:
# Calculates the spectral centroid (brightness) of an audio frame.
spectrum = np.abs(np.fft.rfft(audio_data))
frequencies = np.fft.rfftfreq(len(audio_data), d=1.0 / sample_rate)
magnitude_sum = np.sum(spectrum)
if magnitude_sum == 0:
return 0.0
return float(np.sum(frequencies * spectrum) / magnitude_sum)
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.
- 18d ago First seen · 126 lines · 68 tokens per session scan A f42feef2b2cb
dsp-audio-filter-effects is a skill published in the GitHub repository hamzabellouch/agent-skills (8 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 1,209 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-29.
Other skills, from other repositories
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.
torchtalk-trace
Trace a PyTorch function's cross-language binding chain (Python -> C++ -> CUDA).
dask
Expert Dask distributed computing assistance covering Dask DataFrames, Arrays, Futures, and cluster scaling. Use when analyzing datasets too large for pandas on a single machine or multi-node cluster.
numpy
Expert NumPy numerical computing assistance covering ndarrays, broadcasting, linear algebra, vectorization, and memory views. Use when writing ultra-fast scientific calculations and array operations in Python.
pytorch
Expert PyTorch deep learning assistance covering dynamic tensors, autograd, torch.compile, distributed training (DDP), and GPU acceleration. Use when training neural networks and deploying AI research.
scikit-learn
Expert Scikit-Learn assistance covering classification, regression, clustering, pipelines, cross-validation, and preprocessing. Use when building classical machine learning models and feature engineering pipelines.