layer5-data-wiring

A feature audit that checks whether an application uses real user data and connects available model capabilities to the features that need them.

In plain words
What is it for?
Use it to inspect data flows, find mock or hardcoded values, and check whether relevant model-backed capabilities are actually wired into the product.
Why use it?
It helps reveal features that look complete but display fabricated values or ignore data the application already collects.

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/layer5-data-wiring
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 2,553 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 $0.02553
Opus 5 $0.00000 $0.01277
Sonnet 5 $0.00000 $0.00511
Haiku 4.5 $0.00000 $0.00255

Measured 2d ago against content hash e3a2f48b7da6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

layer5-data-wiring 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/layer5-data-wiring.md · 247 lines

How it starts

The opening of the file, as written. The whole thing — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Layer 5: Data Wiring Audit

Note: Grep commands and concrete examples in this file are drawn from a real workflow-audit run on the Stuffolio codebase (paths like Sources/Features/RepairKeepReplace/, manager names like PriceWatch). The detection patterns are reusable methodology; specific managers and features are project-specific. Substitute your project's equivalents. A full sample scan lives in examples/sample-stuffolio-scan/.

Purpose

Layer 5 verifies that features use real user data instead of mock/hardcoded values, and that model capabilities are fully wired into the features that need them. While Layers 1-4 audit navigation and UX, Layer 5 audits whether the data flowing through those workflows is genuine.

Why This Layer Exists

A feature can pass all navigation audits (correct entry point, proper sheet handling, good feedback) and still be useless if it shows fabricated data. The Repair/Keep/Replace feature was the canonical example: well-architected UI, correct navigation, but the decision engine used a 4-rule if/else chain ignoring repair costs, warranty data, and Price Watch prices that the app already tracked.

The symptom: Feature looks functional. User makes decisions based on it. Data is fake.

What Layer 5 Catches

Issue Type Example Severity
Mock Data asyncAfter delay + hardcoded values simulating a fetch 🔴 Critical
Unwired Data Item has rmaRecords with repair costs, but decision engine ignores them 🟠 High
Placeholder AI "Find Alternatives" button that returns static array 🔴 Critical
Simplified Logic 4-rule if/else when 10+ data points are available 🟠 High
Platform Parity Extension file can't resolve properties on macOS 🟠 High
Unused Integration Price Watch tracks prices, but no feature reads them 🟠 High

Detection Process

Step 1: Model Inventory

Catalog what data the app actually tracks:

Read the full file on GitHub · 247 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 · 247 lines · 0 tokens per session scan A e3a2f48b7da6

Subscribe to this mod's changes

layer5-data-wiring 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 2,553 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.