agentmods.dev

superpowers-sage:pencil-extractor

superpowers-sage:pencil-extractor is an agent for Claude Code from hekivo/superpowers-sage. It costs 61 tokens per session (3,333 once invoked), scanned A, original, MIT.

A design-analysis agent for Pencil, a design tool that stores projects in .pen files. It extracts shared design values, detailed component specifications, or links between Pencil components and Blade components.

In plain words
What is it for?
It is for reviewing a whole Pencil design library, documenting individual sections, or mapping Pencil components to Blade components used in WordPress themes.
Why use it?
It turns Pencil designs into structured information that developers and visual-checking tools can use. It also avoids inventing values when the required Pencil data is unavailable.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the superpowers-sage plugin — 36 skills, 3 commands, 11 agents, 7 hooks shipped together

not rated 13repo 3mo ago A scan 61 tokens original MIT

Good fit It is for reviewing a whole Pencil design library, documenting individual sections, or mapping Pencil components to Blade components used in WordPress themes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hekivo/superpowers-sage/pencil-extractor
View source ↗ hekivo/superpowers-sage
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/hekivo/superpowers-sage

Made for: Claude Code.

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:pencil-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/hekivo/superpowers-sage/pencil-extractor/github.svg)](https://agentmods.dev/agents/hekivo/superpowers-sage/pencil-extractor)
Your own site
<a href="https://agentmods.dev/agents/hekivo/superpowers-sage/pencil-extractor"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/pencil-extractor/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 superpowers-sage:pencil-extractor

Your own site · 80×15
<a href="https://agentmods.dev/agents/hekivo/superpowers-sage/pencil-extractor"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/pencil-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,333 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 $0.00061 $0.03333
Opus 5 $0.00030 $0.01666
Sonnet 5 $0.00012 $0.00667
Haiku 4.5 $0.00006 $0.00333

Measured 8d ago against content hash 598ae1011df0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

superpowers-sage:pencil-extractor 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.

agents/pencil-extractor.md · 339 lines

How it starts

The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Pencil design extraction specialist. You are always invoked by the design-extractor agent — never directly by the user. You read .pen files via Pencil MCP tools and produce structured spec files consumed by the building skill and visual-verifier agent.

MANDATORY: All output artifacts (design specs, token names, component names, section labels) MUST be written in en-US. Never mix languages.

⚠️ MCP AVAILABILITY CONSTRAINT

As a subagent, you may not have access to Pencil MCP (mcp__pencil__*). If dispatched without the tools, verify via ToolSearch for mcp__pencil__batch_get. If absent:

  • Look for pre-captured Pencil data on disk at docs/plans/<plan>/assets/section-<name>.nodes.json and section-<name>-ref.png.
  • If pre-captured data exists, use it as source of truth.
  • If nothing available, return: 
    ⛔ BLOCKED — Pencil MCP unavailable and no pre-captured data on disk.
Caller must either (a) dispatch with Pencil MCP, OR (b) pre-capture nodes + screenshot.

Never fabricate Pencil node trees or values you cannot verify.

Hard requirement — Pencil MCP

First action on start: ToolSearch for mcp__pencil__open_document.

If NOT found:

⛔ BLOCKED — Pencil MCP is not configured.

Install: claude mcp add pencil -- npx -y @anthropic/pencil-mcp
Restart the session after installing.

Golden Rule

The .pen file is always the source of truth. Generated artifacts (spec files, screenshots, component-map) are starting points — not substitutes. Any ambiguity during implementation — exact color value, spacing, node structure — must be resolved by opening the .pen file and querying via batch_get with resolveVariables: true. The live file takes precedence over any saved artifact.

Inputs (provided by design-extractor)

  • mode: PANORAMIC | SURGICAL | COMPONENT_MAP
  • filePath (SURGICAL + COMPONENT_MAP): absolute or relative path to the .pen file
  • sectionId (SURGICAL, optional): Pencil node ID of the section to extract
  • sectionName (SURGICAL, optional): name of the section — used to resolve sectionId if not provided
  • planPath (optional): path to the active plan directory — used for saving assets

Read the full file on GitHub · 339 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. 8d ago First seen · 339 lines · 61 tokens per session scan A 598ae1011df0

Subscribe to this mod's changes

superpowers-sage:pencil-extractor is an agent published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 3,333 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.

Design and UXclient-hekivotier-shared
Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

slide-auditor

Visual layout auditor for RevealJS and Beamer slides. Checks for overflow, font consistency, box fatigue, and spacing issues. Use proactively after creating or modifying slides.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

frontend-reviewer

Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.

everywan-dev/claude-code-engineering · 28 tokens

unity-ui-pro

Build Unity UI — UI Toolkit (UXML/USS/UIDocument) and UGUI (Canvas/RectTransform). Handles screen architecture, data binding, runtime UI performance, gamepad/keyboard input, and cross-platform UI scaling. Use PROACTIVELY for new screens, HUD, menus, in-game dialogs, settings, or any UI work in Unity 2022.3+. Not for…

AcKeskin/contexture · 102 tokens