layer3-issue-detection

A systematic codebase-audit procedure that scans all application entry points and categorises problems such as dead ends and incomplete navigation. An entry point is a place where a user can start an action, such as a button, menu item, or screen.

In plain words
What is it for?
It helps scan navigation and feature entry points, identify missing handlers or destinations, group issues by type and severity, and report findings across the codebase.
Why use it?
It helps find features that lead nowhere, are only partly connected, or cannot be reached, including issues that a detailed check of one user flow might miss. It covers the whole application broadly rather than tracing one path deeply.

Agent

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/terryc21/workflow-audit/layer3-issue-detection
Clone the repo
git clone --depth 1 https://github.com/Terryc21/workflow-audit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 12,289 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 $0.00000 $0.12289
Opus 5 $0.00000 $0.06144
Sonnet 5 $0.00000 $0.02458
Haiku 4.5 $0.00000 $0.01229

Measured 2d ago against content hash 7a08dbe0ac3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

layer3-issue-detection 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.

skills/workflow-audit/agents/layer3-issue-detection.md · 1,426 lines

How it starts

The opening of the file, as written. The whole thing — 1,426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Layer 3: Issue Detection

Note: Specific examples in this file ("Real examples caught in Stuffolio v1.0," concrete file paths like Sources/Features/...) are drawn from a real workflow-audit run on the Stuffolio codebase. They are illustrative — the issue categories are the reusable methodology; the paths and findings are project-specific. A full sample scan lives in examples/sample-stuffolio-scan/.

Purpose

Layer 3 systematically scans ALL entry points from Layer 1 and applies issue detection rules. Unlike Layer 2 (which traces specific flows in depth), Layer 3 does a breadth-first scan to categorize issues across the entire codebase.

Issue Categories

Category 1: Dead Ends

Entry point leads nowhere or to wrong destination.

Detection patterns:

// Navigation to section that doesn't contain the feature
selectedSection = .tools  // but feature not in ToolsView

// Sheet case exists but handler missing
case .featureName  // in enum but no case in sheetContent(for:)

// View exists but no entry point
struct OrphanedFeatureView  // never presented

Severity: 🔴 CRITICAL

Category 2: Incomplete Navigation

User lands on section but must find feature manually.

Detection patterns:

// Section navigation without deep link
selectedSection = .tools  // lands at top, feature buried

// No scroll target or anchor
// No programmatic focus

Severity: 🟠 HIGH

Category 3: Missing Auto-Activation

Feature requires mode/state that isn't set.

Detection patterns:

// Navigation without state setup
selectedSection = .myProducts  // but isSelectMode not set

// Sheet without pre-population
activeSheet = .edit  // but selectedItem not set

Severity: 🟠 HIGH

Category 4: Promise-Scope Mismatch

A specific-sounding CTA opens a generic/overly-broad destination. The user is promised a focused action but gets a container with the action buried among unrelated content.

Different from "Wrong Destination" (user is in the right place, just too much of it) and "Incomplete Navigation" (about scroll position, not destination scope).

Read the full file on GitHub · 1,426 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 · 1,426 lines · 0 tokens per session scan A 7a08dbe0ac3c

Subscribe to this mod's changes

layer3-issue-detection is an agent published in the GitHub repository Terryc21/workflow-audit (58 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 12,289 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.