audit-steps

audit-steps is a command for Claude Code from gustavo-meilus/superpipelines. It costs 40 tokens per session (536 once invoked), scanned A, original, MIT.

A command that checks one or more pipelines against rules for layout, file metadata, structure, connections, and safe execution. It produces a report with findings ranked from SEV-0 to SEV-3, where the levels indicate increasing issue severity.

In plain words
What is it for?
Use it to audit a named pipeline or every available pipeline, check file categories and connections, detect cycles, and review a severity-ranked compliance report.
Why use it?
It finds structural and safety problems with cited evidence before they cause pipeline failures or unsafe runs.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents.

Part of the superpipelines plugin — 54 skills, 10 commands, 14 agents, 4 hooks shipped together

Good fit Use it to audit a named pipeline or every available pipeline, check file categories and connections, detect cycles, and review a severity-ranked compliance report.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gustavo-meilus/superpipelines/audit-steps
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.

Clone the repo
git clone --depth 1 https://github.com/gustavo-meilus/superpipelines

Made for: Claude Code.

Or install superpipelines, the plugin that ships this one along with the rest of its 54 skills, 10 commands, 14 agents, 4 hooks.

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 audit-steps

README.md
[![agentmods](https://agentmods.dev/badge/commands/gustavo-meilus/superpipelines/audit-steps.svg)](https://agentmods.dev/commands/gustavo-meilus/superpipelines/audit-steps)
Your own site
<a href="https://agentmods.dev/commands/gustavo-meilus/superpipelines/audit-steps"><img src="https://agentmods.dev/badge/commands/gustavo-meilus/superpipelines/audit-steps.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 536 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 $0.00040 $0.00536
Opus 5 $0.00020 $0.00268
Sonnet 5 $0.00008 $0.00107
Haiku 4.5 $0.00004 $0.00054

Measured 8d ago against content hash afa87c48cdee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

audit-steps 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 8d 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.

commands/audit-steps.md · 42 lines

What it actually says

Audit Pipeline — Command Reference

Audits one or all pipelines against layout, frontmatter, topology, and runtime-safety standards. Produces a severity-classified report (SEV-0 to SEV-3) with cited evidence.

<operating_modes>

  • Named Pipeline/PathFULL mode: Audits the complete bundle or specific files.
  • --allSCOPE-WIDE mode: Audits every pipeline across all available scopes. </operating_modes>

2. CLASSIFICATION & AUDIT

  • Classify files into categories: subagent, internal skill, entry skill, reference, topology, or registry.
  • Apply the full compliance matrix (see compliance-matrix.md) across the four standard bands plus the resolver-consolidation criteria.
  • Execute topology graph rules, including edge consistency and cycle checks.

3. REPORTING

  • Classify all findings by severity (SEV-0 to SEV-3).
  • The auditor is read-only and never persists; the orchestrator owns persistence, in order:
    1. Ensure <scope-root>/superpipelines/pipelines/{P}/audit/ exists, creating it if missing (idempotent — no-op if present). This MUST precede the write so a fresh pipeline's first audit cannot fail on a missing directory.
    2. Write the auditor's rendered report to audit/latest.md.
    3. Update the last_audit timestamp in registry.json per the auditor's instruction.
  • Present the executive summary inline to the user. If the write fails after the directory is ensured, surface the error and the inline summary so findings are never lost.
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. 8d ago First seen · 42 lines · 40 tokens per session scan A afa87c48cdee

Subscribe to this mod's changes

audit-steps is a command published in the GitHub repository gustavo-meilus/superpipelines (4 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 536 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.