layer2-methodology

A method for tracing a software feature from its starting point, such as a button, through to the user's intended result.

In plain words
What is it for?
It helps review entry points, follow code paths, record state and screen changes, and check whether actions deliver what they promise.
Why use it?
It reveals dead ends, mismatches between labels and destinations, missing feedback, and other problems in a user's journey.

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/layer2-methodology
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 1,532 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 $0.01532
Opus 5 $0.00000 $0.00766
Sonnet 5 $0.00000 $0.00306
Haiku 4.5 $0.00000 $0.00153

Measured 2d ago against content hash 5753d90231b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

layer2-methodology 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/layer2-methodology.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Layer 2: Flow Tracing Methodology

Purpose

Layer 2 takes entry points from Layer 1 and traces the complete user journey:

  • What happens when the user taps?
  • Where do they land?
  • Can they complete their goal?
  • What feedback do they receive?

Tracing Process

Step 1: Identify Entry Point

From Layer 1 inventory, select an entry point to trace.

Step 2: Follow the Code Path

Entry Point → Action → Destination → User Goal

For each step, document:

  • File and line number
  • State changes
  • View transitions
  • Feedback shown

Step 3: Promise Check (CTA-to-Destination Scope)

Compare the CTA label's specificity against the destination view's scope:

CTA Specificity Destination Scope Verdict
Specific ("Track AppleCare+") Focused (ExtendedWarrantyForm) ✅ Match
Specific ("Track AppleCare+") Broad (EditItemSheetWrapper) 🔴 Mismatch
General ("Edit Product") Broad (EditItemSheetWrapper) ✅ Match
General ("Settings") Focused (NotificationSettings) ⚠️ Over-specific

How to assess:

  1. Count concerns in the CTA label (1 = specific, 2+ = general)
  2. Count distinct sections in the destination view
  3. If CTA concerns = 1 but destination sections >= 3 → Promise-Scope Mismatch

Real example caught: "Track AppleCare+" (1 concern) → EditItemSheetWrapper (5+ sections) Fix: Create AppleCareDirectEditSheet wrapping only ExtendedWarrantyFormView

Step 4: Map Expected vs Actual

Aspect Expected Actual Gap?
Landing Feature visible Section landing ⚠️
Scope Focused on CTA promise Broad/generic ⚠️
Feedback Success toast None ⚠️
Next step Clear CTA Ambiguous ⚠️

Step 5: Classify Issue Severity

Severity Description Example
🔴 Critical User cannot complete goal Dead end, crash
🟠 High User confused, extra steps Wrong landing, no feedback
🟡 Medium Friction but completable Slow path, redundant steps
🟢 Low Minor polish Inconsistent wording

Read the full file on GitHub · 193 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 · 193 lines · 0 tokens per session scan A 5753d90231b8

Subscribe to this mod's changes

layer2-methodology 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 1,532 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.