visual-detail-matching

visual-detail-matching is a skill for Claude Code, Codex from UCSC-VLAA/VisualClaw. It costs 31 tokens per session (261 once invoked), scanned A, original, MIT.

A visual-question method for checking every detail in similar answer choices against the objects, colors, materials, tools, and places shown.

In plain words
What is it for?
It is for selecting the most accurate description of what appears in images or video frames.
Why use it?
It helps reject choices containing even one unsupported or contradictory visual detail.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for selecting the most accurate description of what appears in images or video frames.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ucsc-vlaa/visualclaw/visual-detail-matching
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 UCSC-VLAA/VisualClaw --skill visual-detail-matching
Clone the repo
git clone --depth 1 https://github.com/UCSC-VLAA/VisualClaw

Made for: Claude Code, 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.

agentmods badge for visual-detail-matching

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/visual-detail-matching/github.svg)](https://agentmods.dev/skills/ucsc-vlaa/visualclaw/visual-detail-matching)
Your own site
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/visual-detail-matching"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/visual-detail-matching/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.

agentmods 80×15 button for visual-detail-matching

Your own site · 80×15
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/visual-detail-matching"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/visual-detail-matching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00261
Opus 5 $0.00015 $0.00130
Sonnet 5 $0.00006 $0.00052
Haiku 4.5 $0.00003 $0.00026

Measured 9d ago against content hash 5a4873c0a0ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

visual-detail-matching 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 9d 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.

visualclaw/skills_seed/seed_universal_mc/visual-detail-matching/SKILL.md · 18 lines

What it actually says

Match Visual Details Precisely Against Options

  1. Extract specific visual elements: Identify concrete details from images—object types, colors, materials, tools, locations (sink, floor, cup, etc.).
  2. Compare option-by-option: For each option, check if every stated detail appears in the visual evidence.
  3. Flag contradictions: Mark options that describe actions or objects NOT visible in the frames.
  4. Prioritize precision over plausibility: Choose based on what you see, not what sounds reasonable.
  5. Verify descriptive claims: If an option makes a judgment (e.g., "professional," "efficient," "gracefully"), check if the visual evidence supports that characterization.

Example: In the woodworker scenario, option (D) states "few adjustments"—this requires observing actual adjustment attempts in the frames. Option (A) or (C) may sound professional but lack visual support.

Anti-pattern: Selecting an answer because it uses professional language or sounds logical without confirming visual evidence supports every claim.

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. 9d ago First seen · 18 lines · 31 tokens per session scan A 5a4873c0a0ef

Subscribe to this mod's changes

visual-detail-matching is a skill published in the GitHub repository UCSC-VLAA/VisualClaw (55 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 261 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

agui-dotnet-streaming-chat

Get started with the AG-UI .NET SDK: bootstrap and run your first streaming-chat app (client + server) with the AG-UI .NET NuGet packages (AGUI.Client, AGUI.Server, AGUI.Formatting, AGUI.Abstractions). USE FOR: which packages to install and how to wire them; constructing an AGUIChatClient against an endpoint and…

ag-ui-protocol/ag-ui · 223 tokens

agui-dotnet-protobuf

Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…

ag-ui-protocol/ag-ui · 162 tokens

cog-knowledge-consolidation

Build structured knowledge frameworks from scattered vault notes with source attribution.

a5c-ai/babysitter · 19 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

strict-tdd

Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

a5c-ai/babysitter · 34 tokens

plan-implementation

Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.

a5c-ai/babysitter · 29 tokens