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 CassetteTapeCrackle/claude-starters --skill clean-code-audiogit clone --depth 1 https://github.com/CassetteTapeCrackle/claude-startersWrote 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/cassettetapecrackle/claude-starters/clean-code-audio)<a href="https://agentmods.dev/skills/cassettetapecrackle/claude-starters/clean-code-audio"><img src="https://agentmods.dev/badge/skills/cassettetapecrackle/claude-starters/clean-code-audio/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/cassettetapecrackle/claude-starters/clean-code-audio"><img src="https://agentmods.dev/badge/skills/cassettetapecrackle/claude-starters/clean-code-audio.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 | $0.00052 | $0.00441 |
| Opus 5 | $0.00026 | $0.00220 |
| Sonnet 5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
clean-code-audio 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 9d 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.
What it actually says
Clean-code audio / DSP (depth)
Apply on top of the audio-plugin base rules (RT-audio non-negotiables, DSP-is-sacred, golden-buffer tests, pluginval). Also use clean-code-cpp.
The two-thread model
- The audio thread (processBlock) and the message thread (UI, params) never share mutable state via locks.
- Pass parameters across with
std::atomicor a lock-free FIFO; the audio thread only reads smoothed snapshots.
Parameter smoothing
- Never apply a raw parameter jump in the audio path — zipper noise. Smooth it (
juce::SmoothedValueor a one-pole) and read per-sample or per-block.
The inner loop
- Process in blocks; hoist invariants out of the per-sample loop.
- Prefer branch-free math in the hot loop (select/min/max over
if); branches stall the pipeline and hurt determinism. - Prefer
floatunless precision demandsdouble. Flush denormals (ScopedNoDenormals), and design filters/feedback so denormals don't accumulate.
Testability & sacredness
- Keep DSP as pure functions/classes over buffers in
Source/dsp/, decoupled from JUCE UI, so it's unit-testable with signal fixtures and golden buffers (impulse, sine sweep). - DSP is sacred: a golden-buffer test failing on a non-DSP change means something leaked into the algorithm — stop and fix the boundary, don't update the golden file.
Signals it's going wrong
- Allocation/lock/log inside processBlock → move it to the message thread or preallocate.
- A parameter read directly in the loop without smoothing → audible artifacts.
- DSP logic reaching into UI/JUCE component state → break the coupling.
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.
- 9d ago First seen · 30 lines · 52 tokens per session scan A 12429024e270
clean-code-audio is a skill published in the GitHub repository CassetteTapeCrackle/claude-starters (1 stars, last pushed 21d ago), licensed MIT. It adds 52 tokens to every session and 441 once invoked, about $0.0003 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.
Other skills, from other repositories
cpp-reinforcement-learning
C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: Implementing RL algorithms in C++ for performance-critical applications Building production RL systems with libtorch Creating replay buffers and experience storage Optimizing RL training with GPU acceleration…
bun-ffi
This skill should be used when the user asks about "bun:ffi", "foreign function interface", "calling C from Bun", "native libraries", "dlopen", "shared libraries", "calling native code", or integrating C/C++ libraries with Bun.
cpp-rules
C++ coding rules: style, patterns, security, testing. Triggers: .cpp, .cc, .cxx, .hpp, .h, CMakeLists.txt, Makefile, GoogleTest, clang-tidy.
implementing-jsc-classes-cpp
Implements JavaScript classes in C++ using JavaScriptCore. Use when creating new JS classes with C++ bindings, prototypes, or constructors.
symfony:daily-workflow
Daily development workflow for Symfony projects including common tasks, debugging, and productivity tips.
cpp-expert
Expert-level C++ development with modern C++20/23, STL, memory management, and performance. Use when the user mentions C++, C++20, C++23, the STL, templates, or performance, or when the task involves Modern C++ Features, Memory Management, Ranges and Views, or Coroutines.