ml-wireframe

A review step for checking wireframe images—rough screen drawings—so the developer and AI agree on what they show before writing a specification.

In plain words
What is it for?
Use it to review one wireframe image or a folder of wireframes and ask questions about their contents, layout, and reusable parts.
Why use it?
It catches misunderstandings in the screen design before they become detailed plans or code. It can also point out repeated elements and whether reusable wireframes are needed.

Command

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 commands/jpavley/meta-loop-ios/ml-wireframe
Clone the repo
git clone --depth 1 https://github.com/jpavley/meta-loop-ios
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,771 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 $0.00020 $0.01771
Opus 5 $0.00010 $0.00886
Sonnet 5 $0.00004 $0.00354
Haiku 4.5 $0.00002 $0.00177

Measured 2d ago against content hash c62437ea567b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ml-wireframe 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.

commands/ml-wireframe.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Loop: Wireframe Review

Review a wireframe to ensure mutual understanding between developer and AI before specification creation.

Mode: Ask Mode (questions and feedback only, no generation)

Arguments

  • $ARGUMENTS: Path to wireframe image(s) to review
    • Can be a single image path or a directory containing multiple wireframes
    • A directory loads all *-wireframe.png files in it
    • Examples: specs/views/my-feature/main-view-wireframe.png or specs/views/my-feature/

Prerequisites

This skill implements Step 1.2 of the Meta-Loop process defined in skills/meta-loop-methodology/SKILL.md.

The developer should have already drawn the wireframe (Step 1.1) before invoking this review.

Workflow

Phase 1: Load Wireframes

  1. Resolve the path:

    • If $ARGUMENTS is a directory, glob for *.png, *.jpg, *.jpeg files
    • If $ARGUMENTS is a file, load that single image
    • If no argument provided, ask the developer for the wireframe path
  2. Load each wireframe image using the Read tool

  3. Check for reusable view wireframes:

    • Scan for any elements that appear multiple times
    • Note if separate view wireframes exist for reusable patterns

Phase 2: Analyze

Describe your understanding of the wireframe. Cover:

  1. Layout Structure:

    • Overall arrangement (vertical, horizontal, grid, etc.)
    • Major sections and their relationships
    • Spacing and alignment patterns
  2. Views Identified:

    • UI elements visible (buttons, text fields, lists, etc.)
    • Reusable patterns that could be extracted as views
    • Data display areas
  3. Data Flow:

    • What data is being displayed?
    • What user inputs are expected?
    • What state changes might occur?
  4. Interactions:

    • Tappable/clickable elements
    • Navigation triggers
    • Gestures implied
  5. Codebase Patterns:

    • Reference existing patterns from CLAUDE.md that apply
    • Note any existing views that could be reused
    • Identify architectural patterns that fit

Read the full file on GitHub · 236 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 · 236 lines · 20 tokens per session scan A c62437ea567b

Subscribe to this mod's changes

ml-wireframe is a command published in the GitHub repository jpavley/meta-loop-ios (3 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 1,771 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.