Borrowing it
Nothing to install: this file belongs to marcus-w-hobbs/Wilsonic-MTS-ESP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcus-w-hobbs/Wilsonic-MTS-ESP/main/CLAUDE.mdgit clone --depth 1 https://github.com/marcus-w-hobbs/Wilsonic-MTS-ESPWrote 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/instructions/marcus-w-hobbs/wilsonic-mts-esp/claude-md)<a href="https://agentmods.dev/instructions/marcus-w-hobbs/wilsonic-mts-esp/claude-md"><img src="https://agentmods.dev/badge/instructions/marcus-w-hobbs/wilsonic-mts-esp/claude-md/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/instructions/marcus-w-hobbs/wilsonic-mts-esp/claude-md"><img src="https://agentmods.dev/badge/instructions/marcus-w-hobbs/wilsonic-mts-esp/claude-md.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 | $0.04063 | $0.04063 |
| Opus 5.5 | $0.01625 | $0.01625 |
| Sonnet 5.5 | $0.00813 | $0.00813 |
| Haiku 4.5 | $0.00406 | $0.00406 |
Grade A, and why
Wilsonic-MTS-ESP CLAUDE.md 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 16d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build Commands
JUCE version: 9.0.1. The .jucer files resolve modules through the Projucer's
global module path (default ~/JUCE/modules); CI clones the 9.0.1 tag there.
Regenerate Builds/ with Projucer --resave Wilsonic.jucer after pulling.
macOS (Primary Development Platform)
# Build standalone app and plugins using Xcode
open Builds/MacOSX/Wilsonic.xcodeproj
# Select target (Standalone, AU, VST3) and build
# Or build WilsonicController
open Builds/MacOSX-WilsonicController/WilsonicController.xcodeproj
Cross-Platform Build via Command Line
# Linux/CI build (using makefiles)
cd Builds/LinuxMakefile
make -j4 CONFIG=Release
# Run unit tests
make -C tests
./tests/test_wilsonicmath
Windows
# Open in Visual Studio 2022
Builds/VisualStudio2022/Wilsonic.sln
Parallel Development: Lanes and Worktrees
Work flows in three lanes — full contract in CONTRIBUTING.md:
- Plugin (
plugin/*branches):Source/,tests/,*.jucer. Gated by.github/workflows/plugin.yml(JUCE builds + C++ tests + research-seam CLI build). - Research (
research/*branches):experiments/,plans/,prompts/,docs/. Gated by.github/workflows/research.yml(scorer freeze + Python suite). Research readsSource/but NEVER edits it — harness-found plugin bugs become GitHub issues. - Chore (
chore/*branches): docs, CI, scripts.
Non-negotiables for agents:
- One lane per PR. Never mix
Source/andexperiments/changes. - Never edit
experiments/triads/scorer.pyor its pin — CI-enforced freeze; only Marcus changes the scorer. - Choke points are serialized: before touching
WilsonicProcessor+Params.cpp,DesignsModel.*,*.jucer, orall_tunings.json, checkgh pr listfor another open PR touching them. Append-only ordering rules apply (see "Adding New Scale Designs" below). - Worktrees:
scripts/worktree.sh new <lane> <topic>creates.claude/worktrees/<lane>-<topic>on branch<lane>/<topic>;listflags name/branch drift;done <name>is the only sanctioned teardown (stash-safe, refuses unmerged work). If a session auto-created aclaude/*branch, rename to the lane prefix before opening the PR. - One running Wilsonic instance at a time when testing tuning output — MTS-ESP allows one master per machine, and a second worktree's build silently loses the master slot.
- Licences are separate by artefact: all code is MIT, Ear Bench judgments (
experiments/ear_bench/judgments/) are CC BY 4.0, and JUCE's licence applies only to distributing a built plugin binary. Research code must never depend on the real JUCE framework (the research seam builds against stubJuceHeader.hfiles). Details: CONTRIBUTING.md, "Licences: three separate questions".
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.
- 16d ago Changed · +1 lines · +94 tokens per session 7cf0f9550fde
- 27d ago Changed · +5 tokens per session a16e517736c4
- 2mo ago First seen · 333 lines · 3,964 tokens per session scan A cc70b9baf9bc
Wilsonic-MTS-ESP CLAUDE.md is an instructions file published in the GitHub repository marcus-w-hobbs/Wilsonic-MTS-ESP (49 stars, last pushed 6d ago), licensed MIT. It adds 4,063 tokens to every session, about $0.0163 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 2026-08-30.
Wilsonic-MTS-ESP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Wilsonic-MTS-ESP CLAUDE.mdmarcus-w-hobbs/Wilsonic-MTS-ESP | Instructions file | 49 | 6d ago | MIT | A | 4,063 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |