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 agentmods add agents/cpuguy96/stepcovnet/project-layoutgit clone --depth 1 https://github.com/cpuguy96/StepCOVNetWrote 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/agents/cpuguy96/stepcovnet/project-layout)<a href="https://agentmods.dev/agents/cpuguy96/stepcovnet/project-layout"><img src="https://agentmods.dev/badge/agents/cpuguy96/stepcovnet/project-layout.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 | $0.00000 | $0.01516 |
| Opus 5 | $0.00000 | $0.00758 |
| Sonnet 5 | $0.00000 | $0.00303 |
| Haiku 4.5 | $0.00000 | $0.00152 |
Grade A, and why
project-layout 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project layout
When to read: Locating code, configs, scripts, or model artifacts. Routed from AGENTS.md.
Environment conventions
Commands assume repository root as the working directory (clone path is arbitrary).
| Workload | Executable | Notes |
|---|---|---|
CPU pytest, lint, preprocess_dataset.py |
python (project venv activated) |
From repository root |
| GPU train / MERT (WSL) | python after source scripts/wsl_gpu_env.sh |
Override with STEPCOVNET_WSL_PYTHON or WSL_VENV |
| GPU from Windows | python scripts/... |
Auto-dispatch via wsl_gpu.py when the script supports it |
| Checkpoints / callbacks | models_wsl/, callbacks/ |
Gitignored; paths in JSON configs are repo-relative |
Shared WSL shell vars: scripts/wsl_common.sh. See wsl-gpu-stepcovnet.
Pre-push CI mirror: python pre_submit.py (from repository root).
Source
| Path | Contents |
|---|---|
src/stepcovnet/ddc/ |
DDC C-LSTM placement (donahue2017ddc, M-ddc-20ms) |
src/stepcovnet/ddcl/ |
DDCL ConvLSTM placement (omalley2025ddcl, M-slot48) |
src/stepcovnet/onset_events/ |
K-query event onset pipeline (research track) |
src/stepcovnet/onset_ar/ |
Autoregressive onset (gate-tide-overfit …); design AR_ONSET_DESIGN.md; Phase 0+1 implemented — gate failing (EXP-20260627-02) |
src/stepcovnet/dataset_prep/ |
Raw simfile → final_data preprocessing, training_index, training_loader (P8–P9) |
src/stepcovnet/pairing.py |
Audio/chart pairing; list_training_samples for final_data |
src/stepcovnet/mel_onset.py |
Mel spectrogram helpers (shared by dense path; breaks import cycles) |
src/stepcovnet/wsl_gpu.py |
WSL GPU bootstrap / re-exec helpers |
Onset events modules (by pipeline stage):
| Stage | Modules |
|---|---|
| PRE | audio.py, frontend.py, preprocess.py, datasets.py |
| MODEL | models.py, encoder.py, losses.py |
| POST | inference.py |
| METRICS | metrics.py, matching.py, diagnostics.py |
| Train | trainers.py, config.py |
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.
- 3d ago First seen · 103 lines · 0 tokens per session scan A c2ae64e66a3c
project-layout is an agent published in the GitHub repository cpuguy96/StepCOVNet (21 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,516 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 2026-08-30.
Other agents, from other repositories
reviewing-local-changes
Review the current branch's changes for code quality, test coverage, security, best practices, and product/API alignment. Use when asked to perform a code review.
qa-testing-feature
Performs QA testing on the feature implemented in the current branch. Reads specs, docs, and API docstrings, creates a QA test plan, executes tests using Playwright against a debug server, and generates a report with found issues. Use after implementing a feature to validate it meets requirements before finalizing a…
simplifying-local-changes
Simplify and refine code for clarity, consistency, and maintainability while preserving all functionality. Focuses on changes in the current branch.
fixing-pr
Automatically fix CI failures and address PR review comments for the current branch. Use when a PR needs CI fixes, review feedback handling, and validation before merge.
AGENTS
This directory contains custom subagent definitions for Claude Code (and Cursor, which reads from this directory).
CLAUDE
@./AGENTS.md.