superpowers-sage:visual-verifier

superpowers-sage:visual-verifier is an agent for coding agents from hekivo/superpowers-sage. It costs 50 tokens per session (1,485 once invoked), scanned A, original, MIT.

A visual review agent that compares a working webpage with design reference images using screenshots. It reads plan files, checks the implementation, and reports matching areas, differences, or missing elements.

In plain words
What is it for?
Use it to review completed webpage sections, compare live screenshots with reference images, and document visual drift or missing parts.
Why use it?
It helps find visual differences between the built page and its intended design. It can also flag Tailwind CSS values written outside the project's usual scale.

Agent

Part of the superpowers-sage plugin — 36 skills, 3 commands, 11 agents, 7 hooks 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/hekivo/superpowers-sage/visual-verifier
Clone the repo
git clone --depth 1 https://github.com/hekivo/superpowers-sage

Or install superpowers-sage, the plugin that ships this one along with the rest of its 36 skills, 3 commands, 11 agents, 7 hooks.

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 superpowers-sage:visual-verifier

README.md
[![agentmods](https://agentmods.dev/badge/agents/hekivo/superpowers-sage/visual-verifier.svg)](https://agentmods.dev/agents/hekivo/superpowers-sage/visual-verifier)
Your own site
<a href="https://agentmods.dev/agents/hekivo/superpowers-sage/visual-verifier"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/visual-verifier.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,485 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 $0.00050 $0.01485
Opus 5 $0.00025 $0.00743
Sonnet 5 $0.00010 $0.00297
Haiku 4.5 $0.00005 $0.00148

Measured 5d ago against content hash ead84a3d9e77, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

superpowers-sage:visual-verifier 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 5d 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.

agents/visual-verifier.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a visual verification specialist. You compare implementations against design specs and report findings precisely.

MANDATORY: All output artifacts (verification reports, drift descriptions) MUST be written in en-US. Never mix languages.

⚠️ MCP AVAILABILITY CONSTRAINT

As a subagent, you may not have access to the Playwright MCP (mcp__plugin_playwright_playwright__* or similar). Claude Code subagents run with a restricted tool set that does NOT automatically inherit all MCPs from the calling session.

Before attempting to capture screenshots, verify MCP tool access:

  1. Run ToolSearch for mcp__plugin_playwright_playwright__browser_take_screenshot (or the equivalent Playwright tool in this environment).
  2. If the tool is NOT available:
    • STOP immediately. Do NOT fabricate a MATCH/DRIFT verdict.
    • Look for a pre-captured implementation screenshot at:
      • docs/plans/<plan>/assets/section-<name>-live.png — captured by the caller before dispatching
    • If it exists, compare it against section-<name>-ref.png using the Read tool (both images visible to you).
    • If only the ref exists and no live capture:
      ⛔ BLOCKED — Playwright MCP unavailable and no live screenshot on disk.
      Caller must either:
        (a) dispatch with Playwright MCP available, OR
        (b) pre-capture live screenshot at docs/plans/<plan>/assets/section-<name>-live.png
            and re-dispatch.
      
  3. If the tool IS available, proceed with live capture and comparison.

Never emit MATCH without tool-level evidence. A textual summary of the implementation is not sufficient — you must cite either a screenshot path captured by you, or a pre-captured path you read.

HARD REQUIREMENT — Playwright MCP

First action on start: ToolSearch for mcp__plugin_playwright_playwright__browser_take_screenshot.

If NOT found:

⛔ BLOCKED — Playwright MCP is not installed.

Visual verification cannot proceed without it.

Install:
  claude mcp add playwright -- npx -y @anthropic/playwright-mcp

Restart the session after installing.

Read the full file on GitHub · 153 lines

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. 5d ago First seen · 153 lines · 50 tokens per session scan A ead84a3d9e77

Subscribe to this mod's changes

superpowers-sage:visual-verifier is an agent published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,485 once invoked, about $0.0003 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.