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 commands/fannon/u-he-preset-randomizer/documentationgit clone --depth 1 https://github.com/Fannon/u-he-preset-randomizerWrote 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/commands/fannon/u-he-preset-randomizer/documentation)<a href="https://agentmods.dev/commands/fannon/u-he-preset-randomizer/documentation"><img src="https://agentmods.dev/badge/commands/fannon/u-he-preset-randomizer/documentation.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 | $0.00017 | $0.01790 |
| Opus 5 | $0.00009 | $0.00895 |
| Sonnet 5 | $0.00003 | $0.00358 |
| Haiku 4.5 | $0.00002 | $0.00179 |
Grade A, and why
documentation 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 5d 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation & Code Quality Review
Perform a comprehensive review to ensure all documentation reflects the current implementation, TypeScript files have proper headers, and code examples work correctly.
What Gets Reviewed
1. Documentation Files (Priority Order)
- README.md - Installation, CLI examples, MCP setup
- MCP_SERVER.md - MCP tool documentation
- AGENTS.md - Development architecture
- CHANGELOG.md - Version history (current: 1.1.2)
2. Source Code Documentation
- All
src/**/*.tsfiles must have@fileJSDoc headers - Exported functions need JSDoc (when not obvious from types)
- Public API in
src/index.tsfully documented
Review Workflow
Step 1: Scan Repository
Build inventory of:
- Documentation files (*.md)
- TypeScript source files (
src/**/*.ts) - Test files (
src/__tests__/**/*.test.ts) - Configuration (
package.json,tsconfig*.json,biome.json)
Step 2: Verify Documentation Files
README.md
- Installation instructions match
package.json(npx, global install) - CLI examples use current flags
- MCP server setup matches
dist/mcp-server.jsbinary - All links valid (MCP_SERVER.md, AGENTS.md, soundsets)
Current CLI flags:
--synth, --amount, --randomness, --preset, --merge, --pattern, --folder, --category, --author, --favorites, --stable, --binary, --dictionary, --custom-folder, --debug
MCP_SERVER.md
- Tool signatures match
src/mcp-server.tsimplementation - Examples use correct MCP tool names
- Configuration examples are valid JSON
- Claude Desktop setup instructions accurate
Current MCP tools:
list_synths, select_synth, get_current_synth, list_presets, search_presets, filter_presets, explain_preset, get_categories, get_authors, get_favorites_files, generate_random_presets, randomize_presets, merge_presets, get_synth_context
AGENTS.md
- Architecture description matches actual code structure
- File paths accurate
- Development workflow matches
package.jsonscripts - References Biome (not ESLint)
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.
- 5d ago First seen · 246 lines · 17 tokens per session scan A 10dd580f652b
documentation is a command published in the GitHub repository Fannon/u-he-preset-randomizer (32 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 1,790 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
introduce-me
Generate a 2-paragraph personal introduction using the mcp-me introduceme MCP prompt.
ask-about-me
Ask a question about the user's personal profile via the mcp-me MCP server.
publish
Publish a new version of the notebookmd package. Follow these steps exactly.
publish
Guided version release workflow with checks, build, publish, and GitHub Release.
Generate PRPROMPTS
Generate all 32 PRPROMPTS files from PRD with strict PRP pattern.
create-plugin
Guided end-to-end plugin creation workflow with component design, implementation, and validation.