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.
npx agentmods add agents/terryc21/workflow-audit/layer1-patternsgit clone --depth 1 https://github.com/Terryc21/workflow-auditWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.01169 |
| Opus 5 | $0.00000 | $0.00584 |
| Sonnet 5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
layer1-patterns 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layer 1: Pattern Discovery
Note: Examples in this file (sheet enum names, "Discovered: 29 cases in
DashboardSheetType," the "Learnings from Stuffolio Scan" section) are drawn from a real workflow-audit run on the Stuffolio codebase. They are illustrative — substitute the equivalent patterns from your own project. A full sample scan lives inexamples/sample-stuffolio-scan/.
Overview
Layer 1 scans the codebase for UI entry points - places where users can trigger navigation, sheets, or actions. The goal is to create a complete inventory of "things users can tap."
SwiftUI Entry Point Patterns
1. Promotion Cards (HIGH VALUE — may be absent)
Feature discovery cards on dashboard. These are prime workflow audit targets.
# File-based search (grep -l)
PromotionCard\s*\(
CompactPromotionCard\s*\(
# Content extraction (grep -o with context)
PromotionCard\s*\([\s\S]*?title:\s*"([^"]+)"
Note: This pattern may return 0 matches if promotion cards have been removed from the codebase. This is expected — report as "Pattern no longer present (0 matches)" rather than silently skipping.
2. Sheet Triggers (HIGH VALUE)
Central sheet management via enum. Best pattern for auditing.
# Find all sheet case assignments
activeSheet\s*=\s*\.(\w+)
# Find sheet enum definition
enum\s+\w*Sheet\w*\s*:\s*\w+\s*\{[\s\S]*?\}
Discovered: 29 cases in DashboardSheetType, 70+ trigger sites
3. Context Menus (MEDIUM VALUE)
Long-press / right-click actions on list items.
\.contextMenu\s*\{
Discovered: 12 files with context menus
4. Swipe Actions (MEDIUM VALUE)
Swipe gestures on list rows.
\.swipeActions
Discovered: 9 files with swipe actions
5. Navigation Links (MEDIUM VALUE)
Direct navigation without sheets.
NavigationLink\s*\(
Discovered: 6 files (relatively rare - app prefers sheets)
6. Boolean State Triggers (LOW VALUE - TOO BROAD)
The showing\w+ = true pattern matches 155 files. Too noisy for automated scanning.
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.
- yesterday First seen · 138 lines · 0 tokens per session scan A a59e191ef414
layer1-patterns is an agent published in the GitHub repository Terryc21/workflow-audit (58 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,169 tokens. 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 2026-08-30.
Other agents, from other repositories
Native SwiftUI Builder
Builds complex custom SwiftUI views using standard SwiftUI components with TTBaseUIKit design tokens (XView/XSize/XFont). Does NOT use TTBaseSUI wrapper components.
Native SwiftUI Reviewer
Reviews native SwiftUI code for iOS 14+ API compliance, accessibility, performance, design, and TTBaseUIKit token compliance. Does NOT check for TTBaseSUI components.
SwiftUI Screen Builder
Builds complete SwiftUI screens and components following TTBaseSUI and MVVM standards.
Accessibility Audit
Audits iOS accessibility: VoiceOver labels/hints/traits, Dynamic Type, touch targets, color contrast, element grouping.
Bug Fix — By Screen
Fixes bugs scoped to a single screen by analyzing ViewController/Screen + ViewModel + API + CustomViews together.
Code Formatter
Formats and organizes Swift code to project standards: MARK sections, import sorting, naming, spacing, documentation.