pencil-analyzer

pencil-analyzer is an agent for Claude Code from JesusJimenezC/pencil-atelier. It costs 118 tokens per session (2,531 once invoked), scanned C, original, GPL-3.0.

A read-only agent that extracts a structured design brief from Pencil files or selected frames. Pencil is a design-file format for interface layouts.

In plain words
What is it for?
It analyses the design’s visual language and returns a brief with scale guidance and a map of reusable design tokens.
Why use it?
It turns a visual design into documented decisions about mood, colours, geometry, depth, typography, and scale before implementation begins.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter.

Part of the pencil-atelier plugin — 4 skills, 3 agents shipped together

Good fit It analyses the design’s visual language and returns a brief with scale guidance and a map of reusable design tokens.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jesusjimenezc/pencil-atelier/pencil-analyzer
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/JesusJimenezC/pencil-atelier

Made for: Claude Code.

Or install pencil-atelier, the plugin that ships this one along with the rest of its 4 skills, 3 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 pencil-analyzer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jesusjimenezc/pencil-atelier/pencil-analyzer"><img src="https://agentmods.dev/badge/agents/jesusjimenezc/pencil-atelier/pencil-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,531 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00118 $0.02531
Opus 5 $0.00059 $0.01265
Sonnet 5 $0.00024 $0.00506
Haiku 4.5 $0.00012 $0.00253

Measured 9d ago against content hash e72280d077d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

pencil-analyzer scanned grade C with 1 finding 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 9d 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

If the `.pen` is not R3/R4 compliant, set `CONSISTENCY_SIGNALS.coherent: false` and list each issue under `warnings`. Do not refuse the analysis - produce the brief with whatever signal the file carries; the warnings let
agents/pencil-analyzer.md · 215 lines

The source is not reproduced here

Licensed GPL-3.0

The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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. 9d ago First seen · 215 lines · 118 tokens per session scan C e72280d077d6

Subscribe to this mod's changes

pencil-analyzer is an agent published in the GitHub repository JesusJimenezC/pencil-atelier (7 stars, last pushed 4mo ago), licensed GPL-3.0. It adds 118 tokens to every session and 2,531 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

visual-designer

Restructures an already-humanized, fact-checked draft into well-designed, scannable visual components (comparison tables, cited-stat "By the Numbers" grids, authoritative quotations, TL;DR box, glossary cards, sparing callouts) using ONLY native markdown that the project's scoped CSS styles. Never invents facts, never…

XuanRanL/loamwright-SEO-Skill · 101 tokens

audit-visual

Captures desktop and mobile screenshots, evaluates responsive design, above-fold content, touch targets, and image optimization across key pages.

XuanRanL/loamwright-SEO-Skill · 28 tokens

design

UI/UX design agent. Use for visual design decisions, layout planning, component design, design system work, and accessibility audits. Integrates with design-for-ai skills when available.

randomittin/heimdall · 38 tokens

mermaid-expert

Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling. Use proactively for visual documentation, system diagrams, or process flows.

NickCrew/Claude-Cortex · 44 tokens

mermaid-expert

Expert in Mermaid diagramming for documentation and system communication. Produces readable, well-labeled diagrams with both basic and styled variants, plus guidance for rendering and export. Use for flowcharts, sequence diagrams, ERDs, state diagrams, timelines, and architecture views.

NickCrew/Claude-Cortex · 60 tokens

component-architect

Expert in building design systems with focus on component APIs, reusability patterns, and scalable component architectures. Creates flexible, composable, accessible-by-default components.

NickCrew/Claude-Cortex · 37 tokens