What is image-layer-alignment-validator?

A local image-checking skill for comparing two raster images, such as two PNG layers, before combining them in an interactive visual effect.

It compares base and reveal layers, diagnoses drift, recommends shifts or regeneration, and produces local analysis reports.

It helps reveal whether the images show the same scene in the same position, preventing jumps or misalignment during reveals, masks, or morphs.

image-layer-alignment-validator — Skill for Codex by sergekostenchuk

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.

Any agent

npx skills add sergekostenchuk/ui-ux-agent-skill-system --skill image-layer-alignment-validator

Clone the repo

git clone --depth 1 https://github.com/sergekostenchuk/ui-ux-agent-skill-system

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/image-layer-alignment-validator/github.svg)](https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/image-layer-alignment-validator)

Your own site

<a href="https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/image-layer-alignment-validator"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/image-layer-alignment-validator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/image-layer-alignment-validator"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/image-layer-alignment-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 995 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00092	$0.00995
Opus 5.5	$0.00037	$0.00398
Sonnet 5.5	$0.00018	$0.00199
Haiku 4.5	$0.00009	$0.00100

Measured 1mo ago against content hash de89eabaf646, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

image-layer-alignment-validator 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/compare_layers.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

image-layer-alignment-validator — 100% identical, 2 lines differ

core/skills/image-layer-alignment-validator/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image Layer Alignment Validator

Use this skill to check whether two image layers can be composited as the same scene or subject. The goal is not generic image critique; the goal is to decide whether a base layer and reveal layer are spatially compatible.

Modes

compare: analyze two local image files and produce visual/report artifacts.
diagnose: inspect an existing report or screenshots and explain why a reveal/morph looks misaligned.
advise: convert measured drift into concrete fixes: shift, scale, crop, regenerate, or accept.
threshold: tune acceptance thresholds for strict product/portrait work versus looser creative reveal effects.

Workflow

Confirm there are exactly two intended layers: base and reveal/after.
Keep all analysis local by default. Do not upload private images to external services unless the user explicitly requests that.

Run scripts/compare_layers.py when local image paths are available:

python3 $CODEX_SKILLS_DIR/image-layer-alignment-validator/scripts/compare_layers.py \
  --base /path/to/base.png \
  --reveal /path/to/reveal.png \
  --out /path/to/alignment-output

Inspect the generated artifacts before giving a verdict. The script is a deterministic foreground/geometry heuristic; semantic judgment still matters.
If the main subject is ambiguous, read references/subject-taxonomy.md and state the chosen primary subject explicitly.
Score alignment with references/alignment-rubric.md.
Report measured drift and a concrete next action.

Evidence Artifacts

The comparison script writes:

alignment-report.md: human-readable metrics, verdict, and suggested fixes.
alignment-metrics.json: machine-readable dimensions, boxes, drift, IoU, and verdict.
annotated-base.png: detected primary and secondary boxes on the base layer.
annotated-reveal.png: detected primary and secondary boxes on the reveal layer.
side-by-side.png: visual comparison with boxes.
overlay.png: reveal blended over base for quick inspection.
difference.png: amplified pixel difference map.

Read the full file on GitHub · 98 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 98 lines · 92 tokens per session scan A de89eabaf646

Subscribe to this mod's changes

image-layer-alignment-validator is a skill published in the GitHub repository sergekostenchuk/ui-ux-agent-skill-system (32 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 995 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.

Creative and media Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

image-layer-alignment-validator