audit-workflow

audit-workflow is a cursor rule for Cursor from beettlle/pi-spine. It costs 11 tokens per session (1,237 once invoked), scanned A, original, MIT.

A rule-based review process that checks whether a development phase or milestone is truly complete before work continues.

In plain words
What is it for?
It helps trigger detailed audits for completed phases, milestones, and quality concerns across Swift, iOS, and Python projects.
Why use it?
It catches code-quality and project issues that may be missed when a phase is marked complete too quickly.

Cursor rule for Cursor

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 rules/beettlle/pi-spine/audit-workflow
Clone the repo
git clone --depth 1 https://github.com/beettlle/pi-spine

Made for: Cursor.

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-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/beettlle/pi-spine/audit-workflow.svg)](https://agentmods.dev/rules/beettlle/pi-spine/audit-workflow)
Your own site
<a href="https://agentmods.dev/rules/beettlle/pi-spine/audit-workflow"><img src="https://agentmods.dev/badge/rules/beettlle/pi-spine/audit-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,237 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 $0.00011 $0.01237
Opus 5 $0.00005 $0.00619
Sonnet 5 $0.00002 $0.00247
Haiku 4.5 $0.00001 $0.00124

Measured 3d ago against content hash 5e3282fdf215, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-workflow 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 3d 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.

.cursor/rules/audit-workflow.mdc · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Completion Audit Workflow

This rule provides guidance for running brutal audits after completing a development phase or milestone.

When to Run Audits

Apply this workflow when:

  • The user mentions completing a "Phase" or "Milestone"
  • The user asks to "verify phase completion"
  • The user wants to ensure code quality before proceeding to the next phase
  • Code quality concerns arise during development

Available Audit Workflows

The repository includes comprehensive brutal audit workflows:

Swift/iOS Projects (Swift 5.9)

  • File: swift-5-9-brutal-audit.mdc
  • Use when: Swift 5.9 language mode (platform minimum is project-defined)
  • Covers: Architectural patterns, concurrency, performance, test quality, Swift 6 readiness, UI compliance

Swift/iOS Projects (Swift 6)

  • File: swift-6-brutal-audit.mdc
  • Use when: Swift 6 language mode (platform minimum is project-defined)
  • Covers: Architectural patterns, strict concurrency compliance, performance, test quality, UI compliance

Python Projects

  • File: python-3-brutal-audit.mdc
  • Use when: Working on Python 3.13+ projects
  • Covers: Async/await patterns, layer boundaries, performance, test quality, type safety, web compliance

Java Projects

  • File: java-brutal-audit.mdc
  • Use when: Working on Java 17 or Java 21 LTS projects
  • Covers: Concurrency (ExecutorService/Virtual Threads), layer boundaries, Effective Java patterns, Optional/Records, test quality, JVM tuning

Go Projects

  • File: go-1-21-brutal-audit.mdc
  • Use when: Working on Go 1.21+ projects
  • Covers: Effective Go, concurrency, testing, structure

JavaScript/TypeScript Projects

  • File: javascript-3-brutal-audit.mdc
  • Use when: Working on JavaScript/TypeScript projects
  • Covers: Modern ES, tooling, testing

Rust Projects

  • File: rust-brutal-audit.mdc
  • Use when: Working on Rust (edition 2021 or 2024) projects
  • Covers: Error handling, ownership, async/concurrency, testing, API guidelines, unsafe

Read the full file on GitHub · 121 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. 3d ago First seen · 121 lines · 11 tokens per session scan A 5e3282fdf215

Subscribe to this mod's changes

audit-workflow is a cursor rule published in the GitHub repository beettlle/pi-spine (3 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,237 once invoked, about $0.0001 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.