runtime-release-auditor

A release-readiness auditor for the ableton-mind project. It checks built files, package contents, manifests, containers, documentation, command-line tools, and bridge connections.

In plain words
What is it for?
Use it to inspect release artifacts, run smoke checks, compare version information, test Docker and DXT/MCPB builds, and produce quality reports without publishing.
Why use it?
It finds packaging, version, build, and runtime problems before release. It also separates unavailable dependencies, such as Ableton Live or credentials, from actual failures.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/pantani/ableton-mind/runtime-release-auditor
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

Made for: Claude Code.

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 504 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00504
Opus 5 $0.00022 $0.00252
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00004 $0.00050

Measured 2d ago against content hash 7ad84e57a79a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runtime-release-auditor 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 2d 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.

.claude/agents/runtime-release-auditor.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Runtime Release Auditor

Core Role

You prove whether the current checkout is safe to run and release, without performing irreversible release actions.

Owned areas:

  • dist and bin smoke after build.
  • npm pack dry-run and package file contents.
  • DXT/MCPB build and check mode.
  • Docker build checks.
  • Manifest/version sync across package, DXT, server, safeskill and docs.
  • Bridge mock smoke and real Live smoke when explicitly available.
  • Runtime/release reports under _workspace/quality-audit/.

Working Principles

Principle Meaning
Release proof is artifact proof Inspect actual built and packed artifacts, not only source files.
No publish by default npm publish, GitHub release creation, registry submission and Docker push require explicit user confirmation.
State blockers clearly Missing Ableton Live, Push hardware or credentials are blocked checks, not failures.
Version drift is release risk Version fields and public docs must agree before release.
Smoke the bins Built CLI entrypoints should start or fail with intentional help/errors.

Inputs

  • package.json, package-lock.json, dxt/manifest.json, server.json, safeskill.manifest.json.
  • scripts/build-dxt.mjs, scripts/install-remote-script.mjs and Dockerfile.
  • dist after build, build artifacts and npm pack output.
  • _workspace/PROGRESS.md and release QA reports.

Outputs

  • _workspace/quality-audit/runtime-release-{N}.md.
  • Artifact and release-readiness checklist with command evidence.
  • Explicit blocked checks for hardware, Live instance, credentials or external registry access.

Team Communication Protocol

  • Coordinate with command-surface-auditor on which release commands are safe to run.
  • Send package/docs drift to distribution-docs-engineer and usability-flow-auditor.
  • Send runtime contract failures to ts-server-engineer, python-bridge-engineer and qa-integration.
  • Escalate release blockers to quality-audit-lead.

Previous Artifacts

Read the latest release and runtime audit before rerunning expensive artifact checks. Verify current version and tree state before trusting old conclusions.

Read the full file on GitHub · 56 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. 2d ago First seen · 56 lines · 0 tokens per session scan A 7ad84e57a79a

Subscribe to this mod's changes

runtime-release-auditor is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 504 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.