ve-verifier-deck-review

ve-verifier-deck-review is an agent for Claude Code from theclaymethod/artifacture. It costs 34 tokens per session (294 once invoked), scanned A, original, MIT.

A review agent for checking rendered slide decks: the actual images of slides and their interactive states. It returns a JSON verdict about whether the deck passes its review criteria.

In plain words
What is it for?
Use it to audit slide titles and narratives, annotations, reading paths, base and progressive states, click-in behavior, and variety between neighboring slides.
Why use it?
It catches problems that may not be visible in source files, such as misleading content, unclear reading order, weak slide variety, or broken changes between states.

Agent for Claude Code

Part of the visual-explainer plugin — 1 skill, 13 commands, 11 agents shipped together

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 agents/theclaymethod/artifacture/ve-verifier-deck-review
Clone the repo
git clone --depth 1 https://github.com/theclaymethod/artifacture

Made for: Claude Code.

Or install visual-explainer, the plugin that ships this one along with the rest of its 1 skill, 13 commands, 11 agents.

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 ve-verifier-deck-review

README.md
[![agentmods](https://agentmods.dev/badge/agents/theclaymethod/artifacture/ve-verifier-deck-review.svg)](https://agentmods.dev/agents/theclaymethod/artifacture/ve-verifier-deck-review)
Your own site
<a href="https://agentmods.dev/agents/theclaymethod/artifacture/ve-verifier-deck-review"><img src="https://agentmods.dev/badge/agents/theclaymethod/artifacture/ve-verifier-deck-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 294 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 $0.00034 $0.00294
Opus 5 $0.00017 $0.00147
Sonnet 5 $0.00007 $0.00059
Haiku 4.5 $0.00003 $0.00029

Measured 4d ago against content hash 4ca4e809c254, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ve-verifier-deck-review 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 4d 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.

plugins/visual-explainer/.claude/agents/ve-verifier-deck-review.md · 38 lines

What it actually says

ve-verifier-deck-review

Run one audit pass. Do not fix files.

Read

  1. plugins/visual-explainer/scripts/verify/rubrics/pass-deck-review.md
  2. One generated deck-review-*.json manifest.
  3. Every review_groups entry in manifest order. Dispatch each group as its exact two-frame evidence package; do not flatten the deck into one oversized request. The route is ready only when its independently qualified batch_size is 2. Capture fails closed when a state has no valid base, progression, drill, or adjacent-slide partner.
  4. A visible title or one-sentence narrative job only when the frame does not supply one.

Treat the rendered pixels as truth. Complete every group so every base, drill, and progressive state is reviewed and adjacent base-slide pairs are checked for structural variety. Do not infer intent from implementation source or the builder's explanation.

Output

Return only one valid JSON object matching the rubric schema:

{"pass":true,"findings":[]}

Do not include prose, markdown, code fences, summaries, or recommendations outside findings.

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. 4d ago First seen · 38 lines · 34 tokens per session scan A 4ca4e809c254

Subscribe to this mod's changes

ve-verifier-deck-review is an agent published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 12d ago), licensed MIT. It adds 34 tokens to every session and 294 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 2026-08-31.