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 Fannon/u-he-preset-randomizer --skill documentation-reviewgit 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/skills/fannon/u-he-preset-randomizer/documentation-review)<a href="https://agentmods.dev/skills/fannon/u-he-preset-randomizer/documentation-review"><img src="https://agentmods.dev/badge/skills/fannon/u-he-preset-randomizer/documentation-review/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/fannon/u-he-preset-randomizer/documentation-review"><img src="https://agentmods.dev/badge/skills/fannon/u-he-preset-randomizer/documentation-review.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 | $0.00047 | $0.01594 |
| Opus 5 | $0.00023 | $0.00797 |
| Sonnet 5 | $0.00009 | $0.00319 |
| Haiku 4.5 | $0.00005 | $0.00159 |
Grade A, and why
documentation-review 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 11d 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Review Skill
This skill proactively identifies documentation issues and suggests fixes for the u-he-preset-randomizer project.
When to Activate
Automatically trigger this skill when:
- User mentions documentation being out of date
- User asks about API examples or how to use features
- After making significant changes to exported functions or public APIs
- When user mentions adding features that need documentation
- User asks to review or update docs
- After modifying CLI flags or MCP tools
Project Context
u-he-preset-randomizer - CLI tool and MCP server for u-he synth preset generation:
- CLI interface (
src/cli.ts) - Main command-line tool - MCP server (
src/mcp-server.ts) - Model Context Protocol server for AI assistants - Core modules: parser, analyzer, randomizer, preset library
- Synth support: Diva, Hive, Repro-1, Repro-5, Zebra2, ZebraHZ, Zebralette3, and more
Quick Documentation Checks
1. Core Documentation Files
- README.md - Installation, CLI usage, MCP setup
- MCP_SERVER.md - MCP tool documentation and examples
- AGENTS.md - Development architecture and workflows
- CHANGELOG.md - Version history (current: 1.1.2)
2. CLI Examples Validation
Verify examples use correct flags:
--synth- Synth name (e.g., Diva, Hive)--amount- Number of presets to generate--randomness- Percentage (0-100) for randomization--preset- Base preset name or?for random--merge- Preset names to merge (can be multiple)--pattern- Glob pattern for preset filtering--folder- Filter by folder path--category- Filter by category--author- Filter by author--favorites- Filter by .uhe-fav file--stable- Use stable randomization mode--binary- Include binary section (⚠️ may cause crashes)--dictionary- Use dictionary for random names--custom-folder- Custom u-he installation path--debug- Enable debug logging
3. MCP Tool Signatures
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.
- 11d ago First seen · 217 lines · 47 tokens per session scan A 409bfadc6b36
documentation-review is a skill published in the GitHub repository Fannon/u-he-preset-randomizer (32 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 1,594 once invoked, about $0.0002 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 skills, from other repositories
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
fin-brief-generator
A tool for creating or updating FIN_BRIEF.md, a structured research brief for a financial or economics study. It can use existing research files or ask for missing information.
git-iris
Use this skill when generating commit messages, pull request descriptions, release notes, changelogs, or code reviews in a repository where git-iris is available. Activates on requests like "commit this", "write a commit message", "draft a PR", "generate release notes", "write a changelog", or "review my changes" when…
excalidraw-diagram-generator
Generate .excalidraw diagrams from natural language. Use when creating flowcharts, mind maps, system architecture diagrams, sequence diagrams, ER diagrams, network diagrams, or any visual process visualization.
gemini-image-generator
Use when generating professional posed product images for e-commerce using Gemini AI with optimized prompts.
clay-art-video-generator
Use when clay art video generator skill.