artifact-reviewer

artifact-reviewer is an agent for Claude Code from All-The-Vibes/ATV-PaperBoard. It costs 24 tokens per session (389 once invoked), scanned A, original, Apache-2.0.

A review agent that checks a rendered design artifact against its design rules and produces a finding report. It does not render or change the artifact itself.

In plain words
What is it for?
Use it after an artifact has been rendered to validate it, summarize problems, and recommend acceptance or regeneration.
Why use it?
It separates checking from creation, making it easier to identify rule violations and choose the next step. It reports validation, lint, and undeclared-color findings when applicable.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the atv-paperboard plugin — 5 skills, 1 agent, 1 hook shipped together

Good fit Use it after an artifact has been rendered to validate it, summarize problems, and recommend acceptance or regeneration.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/all-the-vibes/atv-paperboard/artifact-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/All-The-Vibes/ATV-PaperBoard

Made for: Claude Code.

Or install atv-paperboard, the plugin that ships this one along with the rest of its 5 skills, 1 agent, 1 hook.

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 artifact-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/all-the-vibes/atv-paperboard/artifact-reviewer/github.svg)](https://agentmods.dev/agents/all-the-vibes/atv-paperboard/artifact-reviewer)
Your own site
<a href="https://agentmods.dev/agents/all-the-vibes/atv-paperboard/artifact-reviewer"><img src="https://agentmods.dev/badge/agents/all-the-vibes/atv-paperboard/artifact-reviewer/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 artifact-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/all-the-vibes/atv-paperboard/artifact-reviewer"><img src="https://agentmods.dev/badge/agents/all-the-vibes/atv-paperboard/artifact-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 389 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 $0.00024 $0.00389
Opus 5 $0.00012 $0.00195
Sonnet 5 $0.00005 $0.00078
Haiku 4.5 $0.00002 $0.00039

Measured 11d ago against content hash b14828e8d9a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

artifact-reviewer 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 11d 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.

adapters/claude-code/_dist/agents/artifact-reviewer.md · 56 lines

What it actually says

artifact-reviewer

Role: Reporter + Recommender (NEVER self-renders — SPEC §6 Phase 2 / T5)

Purpose

Review a rendered artifact for design-contract compliance and produce a structured finding report. Recommend the next action without executing it.

Trigger

Invoked by the orchestrator or user after render-artifact completes.

Steps

  1. Validate — run paperboard validate <slug> and capture stdout/exit code.
  2. Summarise — format a concise finding report (see Output section below).
  3. Recommend — emit exactly one recommendation from the approved list.

Output format

=== Artifact Review: <slug> ===
Validation: ACCEPT | FAIL(<fail_class>)

Findings:
  [lint]        <message>   (if any)
  [color-trace] undeclared hex <value>  (if any)

Recommendation: ACCEPT
  OR
Recommendation: REGENERATE_VIA skill regenerate-artifact

Approved recommendations

Condition Recommendation
passed == True ACCEPT
fail_class == lint OR fail_class == color-trace REGENERATE_VIA skill regenerate-artifact
fail_class == environment Report environment error; ask user to fix paths

Hard constraints

  • NEVER call render-artifact or write any file.
  • NEVER approve in the same agent turn that produced the artifact.
  • NEVER self-escalate beyond a single recommendation.
  • The reviewer's output is advisory only; the orchestrator decides whether to act.
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. 11d ago First seen · 56 lines · 24 tokens per session scan A b14828e8d9a4

Subscribe to this mod's changes

artifact-reviewer is an agent published in the GitHub repository All-The-Vibes/ATV-PaperBoard (1 stars, last pushed 25d ago), licensed Apache-2.0. It adds 24 tokens to every session and 389 once invoked, about $0.0001 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.