multiple-choice-precision-matching

multiple-choice-precision-matching is a skill for Claude Code, Codex from UCSC-VLAA/VisualClaw. It costs 37 tokens per session (263 once invoked), scanned A, original, MIT.

A method for choosing the multiple-choice option that precisely matches what a video question asks.

In plain words
What is it for?
Use it when deciding whether a video shows recurring actions, turning points, an overall activity, or the core process.
Why use it?
It avoids selecting an option merely because it shares keywords while being too broad, too narrow, or partly unrelated.

Skill for Claude CodeCodex

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

Good fit Use it when deciding whether a video shows recurring actions, turning points, an overall activity, or the core process.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ucsc-vlaa/visualclaw/multiple-choice-precision-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 multiple-choice-precision-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 multiple-choice-precision-matching

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/multiple-choice-precision-matching.svg)](https://agentmods.dev/skills/ucsc-vlaa/visualclaw/multiple-choice-precision-matching)
Your own site
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/multiple-choice-precision-matching"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/multiple-choice-precision-matching.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 263 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 $0.00037 $0.00263
Opus 5 $0.00018 $0.00131
Sonnet 5 $0.00007 $0.00053
Haiku 4.5 $0.00004 $0.00026

Measured 8d ago against content hash e74f357edd52, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

multiple-choice-precision-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 8d 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/multiple-choice-precision-matching/SKILL.md · 21 lines

What it actually says

Match Question Scope to Answer Precision

  1. Identify what the question is asking:
    • Recurring actions? → Look for repeated patterns across the video
    • Key turning points? → Look for crucial moments, not routine actions
    • Overarching activity? → Look for the main shared activity, not individual actions
    • Core process? → Look for the essential steps, not all variations
  2. Reject options that are too broad or include unrelated elements.
  3. Reject options that describe only part of the activity or add contradictory details.
  4. Cross-reference: Does this option directly answer the specific question asked?

Example: Question asks for "key turning points" → Option D ("walks, puts hands on knees, lifts hands") is routine movement, not a turning point. Option C ("tackles the ball") is a decisive moment.

Anti-pattern: Selecting an option because it mentions relevant words (e.g., "walking") without verifying it answers the actual question being asked (e.g., turning points vs. recurring actions).

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. 8d ago First seen · 21 lines · 37 tokens per session scan A e74f357edd52

Subscribe to this mod's changes

multiple-choice-precision-matching is a skill published in the GitHub repository UCSC-VLAA/VisualClaw (55 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 263 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.