presonus-studiolive-mcp: Skill for Claude Code

.github/Skills/repo-truth-maintenance/SKILL.md

repo-truth-maintenance is a skill for Claude Code, Codex from zarfld/presonus-studiolive-mcp. It costs 32 tokens per session (1,243 once invoked), scanned A, original, MIT.

A maintenance skill for keeping repository documentation aligned with the code and verified evidence. A repository is the project folder and its version-controlled history.

In plain words
What is it for?
Use it when reviewing or editing documentation, version and release claims, hardware-support statements, process text, or statements such as “production-ready” and “fully validated.”
Why use it?
It helps prevent README files and release text from overstating implementation status, hardware support, testing, or licensing details.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is zarfld/presonus-studiolive-mcp's own configuration. It tells Claude Code and Codex how to work on presonus-studiolive-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything presonus-studiolive-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to zarfld/presonus-studiolive-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/zarfld/presonus-studiolive-mcp/master/.github/Skills/repo-truth-maintenance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/zarfld/presonus-studiolive-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for repo-truth-maintenance

README.md
[![agentmods](https://agentmods.dev/badge/skills/zarfld/presonus-studiolive-mcp/repo-truth-maintenance/github.svg)](https://agentmods.dev/skills/zarfld/presonus-studiolive-mcp/repo-truth-maintenance)
Your own site
<a href="https://agentmods.dev/skills/zarfld/presonus-studiolive-mcp/repo-truth-maintenance"><img src="https://agentmods.dev/badge/skills/zarfld/presonus-studiolive-mcp/repo-truth-maintenance/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.

agentmods 80×15 button for repo-truth-maintenance

Your own site · 80×15
<a href="https://agentmods.dev/skills/zarfld/presonus-studiolive-mcp/repo-truth-maintenance"><img src="https://agentmods.dev/badge/skills/zarfld/presonus-studiolive-mcp/repo-truth-maintenance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,243 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01243
Opus 5 $0.00016 $0.00622
Sonnet 5 $0.00006 $0.00249
Haiku 4.5 $0.00003 $0.00124

Measured 12d ago against content hash 556b6d63b45f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

repo-truth-maintenance 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 12d 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.

.github/Skills/repo-truth-maintenance/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo truth maintenance

Use this skill when

Use this skill when editing or reviewing:

  • README.md
  • status/version/release claims
  • hardware support statements
  • license text
  • “complete”, “field-ready”, “v1.0”, “all”, “fully”, “production-ready”, “validated”, or similar claims
  • generated or template-derived process text
  • documentation that lists MCP tools/resources, supported mixer models, firmware versions, or validation coverage

Goal

Prevent the repository from claiming more than the code and verification artifacts prove.

The repository may describe planned or inferred capability, but it must label it explicitly. The README must be a product-status document, not a mixture of product truth and generic lifecycle-template marketing.

Required claim categories

Every nontrivial capability claim must fit one category:

Category Meaning Allowed wording
verified Confirmed by automated tests or hardware evidence linked from the repo “verified on …”, “tested by …”
implemented-unverified Code exists, but no HIL/probe evidence yet “implemented, not hardware-verified”
inferred Derived from live state keys or reverse engineering, not probe-confirmed “inferred from live state”
probe-required Requires operator-driven diff/probe before reliable use “probe required”
stub Tool/schema exists but deliberately returns limited result “stub”, “returns instructions only”
planned Backlog item only “planned”, “not implemented”
unsupported Out of scope or blocked “not supported”

Procedure

  1. Inspect implementation before editing documentation.
    • Check packages/presonus-mcp-server/src/tools.ts for registered tools.
    • Check packages/presonus-mcp-server/src/resources.ts for registered resources.
    • Check package.json and package-level package.json files for actual version numbers and scripts.
    • Check HIL fixtures, HIL tests, captured probe output, and validation docs before writing hardware-support claims.

Read the full file on GitHub · 117 lines

Changes

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.

  1. 12d ago First seen · 117 lines · 32 tokens per session scan A 556b6d63b45f

Subscribe to this mod's changes

repo-truth-maintenance is a skill published in the GitHub repository zarfld/presonus-studiolive-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,243 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 2026-08-31.