semantic-precision-matching

semantic-precision-matching is a skill for Claude Code, Codex from UCSC-VLAA/VisualClaw. It costs 35 tokens per session (273 once invoked), scanned A, original, MIT.

A video-question method for comparing the exact meaning of similar answer choices, including the action, object, and whether it happens once or repeatedly.

In plain words
What is it for?
It is for distinguishing processes such as grinding and polishing, sharpening, and cutting based on what the video actually shows.
Why use it?
It prevents near-matching answers from being selected just because they use similar words.

Skill for Claude CodeCodex

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

Good fit It is for distinguishing processes such as grinding and polishing, sharpening, and cutting based on what the video actually shows.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/semantic-precision-matching.svg)](https://agentmods.dev/skills/ucsc-vlaa/visualclaw/semantic-precision-matching)
Your own site
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/semantic-precision-matching"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/semantic-precision-matching.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 273 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 $0.00035 $0.00273
Opus 5 $0.00017 $0.00137
Sonnet 5 $0.00007 $0.00055
Haiku 4.5 $0.00003 $0.00027

Measured 8d ago against content hash f22ea8d9eb6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

semantic-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/semantic-precision-matching/SKILL.md · 22 lines

What it actually says

Match Precise Semantic Details to Video Content

  1. Identify key semantic distinctions between similar options (e.g., "grind and polish" vs. "sharpen" vs. "cut").
  2. For each option, extract the core claim: What specific process or action is being described?
  3. Cross-reference each claim against what the video actually demonstrates—look for exact verb and object matches.
  4. Pay attention to frequency markers: "repeatedly," "once," "consistently" must align with observed behavior.
  5. Reject options where the semantic content (the actual process described) does not match the video, even if the option is well-constructed.

Example: Options describe: (A) grind and polish, (C) sharpen, (E) cut Video shows: grinding and polishing motions Correct: (A) — exact semantic match Incorrect: (C) or (E) — different processes not observed

Anti-pattern: Selecting an option because it uses similar keywords without verifying the core semantic claim (the actual process or action) is demonstrated in the video.

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 · 22 lines · 35 tokens per session scan A f22ea8d9eb6d

Subscribe to this mod's changes

semantic-precision-matching is a skill published in the GitHub repository UCSC-VLAA/VisualClaw (55 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 273 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.