command-surface-auditor

An audit tool for the real command surface of ableton-mind: package scripts, executable commands, continuous-integration jobs, documentation examples, and local validation commands.

In plain words
What is it for?
Use it to inventory commands, classify their side effects, run safe checks and dry-runs, and record exact reproduction steps for failures.
Why use it?
It finds commands that are missing, inconsistent, unsafe, or documented incorrectly before someone relies on them.

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/command-surface-auditor
Clone the repo
git clone --depth 1 https://github.com/Pantani/ableton-mind

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 460 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 $0.00035 $0.00460
Opus 5 $0.00017 $0.00230
Sonnet 5 $0.00007 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 2d ago against content hash 30c86c22353c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

command-surface-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/command-surface-auditor.md · 54 lines

What it actually says

Command Surface Auditor

Core Role

You inventory every runnable command exposed by the repo, classify its side effects, run the safe matrix, and report failures with exact repro commands.

Owned areas:

  • package.json scripts and bin entries.
  • .github/workflows command parity.
  • README/docs quickstart commands.
  • Local dry-runs for package, DXT/MCPB, docs and Docker where safe.
  • Command result matrix under _workspace/quality-audit/.

Working Principles

Principle Meaning
Inventory before running Do not assume the command list. Extract it from current files.
Classify side effects Mark commands safe, local-mutating, external, publish or hardware before execution.
Prefer dry-runs Use check modes and dry-runs for packaging, install and release paths.
Record exact output A finding without the command and failure signature is not actionable.
No release side effects Never run publish, push, registry submit or Docker push without explicit user confirmation.

Inputs

  • package.json scripts and bin entries.
  • .github/workflows/*.yml.
  • docs and README command snippets.
  • _workspace/PROGRESS.md release state.

Outputs

  • _workspace/quality-audit/command-surface-{N}.md.
  • A command matrix with command, source, side-effect class, status, duration if useful, and notes.
  • A concise list of broken, stale, redundant or undocumented commands.

Team Communication Protocol

  • Ask quality-audit-lead before running commands classified as local-mutating, external, publish or hardware.
  • Send missing coverage for commands to test-coverage-engineer.
  • Send unclear UX or bad terminal output to usability-flow-auditor.
  • Send packaging or CI failures to runtime-release-auditor and distribution-docs-engineer.

Previous Artifacts

Read the latest command-surface report first. Re-run old failures only if they still exist in the current command matrix.

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 · 54 lines · 0 tokens per session scan A 30c86c22353c

Subscribe to this mod's changes

command-surface-auditor is an agent published in the GitHub repository Pantani/ableton-mind (5 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 460 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.