behavioral-inference-validation

behavioral-inference-validation is a skill for Claude Code, Codex from UCSC-VLAA/VisualClaw. It costs 31 tokens per session (251 once invoked), scanned A, original, MIT.

A video-question method for judging behavior from the person’s full sequence of actions instead of one isolated moment.

In plain words
What is it for?
It is for deciding whether someone is exploring, acting methodically, or following another pattern shown throughout a video.
Why use it?
It reduces incorrect guesses about intent based on a single action that may not represent the overall behavior.

Skill for Claude CodeCodex

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 skills/ucsc-vlaa/visualclaw/behavioral-inference-validation
Any agent
npx skills add UCSC-VLAA/VisualClaw --skill behavioral-inference-validation
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 behavioral-inference-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/behavioral-inference-validation.svg)](https://agentmods.dev/skills/ucsc-vlaa/visualclaw/behavioral-inference-validation)
Your own site
<a href="https://agentmods.dev/skills/ucsc-vlaa/visualclaw/behavioral-inference-validation"><img src="https://agentmods.dev/badge/skills/ucsc-vlaa/visualclaw/behavioral-inference-validation.svg" alt="Measured on agentmods" 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 251 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 5.1 $0.00031 $0.00251
Opus 5 $0.00015 $0.00125
Sonnet 5 $0.00006 $0.00050
Haiku 4.5 $0.00003 $0.00025

Measured 6d ago against content hash 255745163c3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

behavioral-inference-validation 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 6d 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/behavioral-inference-validation/SKILL.md · 21 lines

What it actually says

Validate Behavioral Inferences Against Full Action Sequence

  1. Collect all observed actions and interactions throughout the video, not just isolated moments.
  2. Identify the overall pattern: Are actions goal-directed, exploratory, disorganized, efficient, etc.?
  3. Match the inferred behavioral pattern to the option that best summarizes the cumulative evidence.
  4. Reject inferences based on single actions (e.g., "picking up a fork" or "taking a break") if the overall pattern contradicts that inference.
  5. Prioritize options describing ongoing, consistent patterns over options describing isolated events or exceptions.

Example: Observed actions: Character explores multiple rooms, interacts with various objects, examines surroundings methodically. Correct inference: "exploring the house and interacting with objects" (pattern-based). Incorrect inference: "trying to turn off lights" or "trying to escape" (isolated action or assumption).

Anti-pattern: Inferring intent from a single action or moment without considering the full sequence of behaviors and the overall context of 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. 6d ago First seen · 21 lines · 31 tokens per session scan A 255745163c3a

Subscribe to this mod's changes

behavioral-inference-validation 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 251 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