illustration:popa

illustration:popa is a skill for Claude Code from stevengonsalvez/agents-in-a-box. It costs 85 tokens per session (830 once invoked), scanned A, original, MIT.

A skill for generating detailed, readable sketchnote illustrations featuring Popa, a pink blob with a green sprout and notepad.

In plain words
What is it for?
Use it for system explainers, architecture diagrams, product walkthroughs, how-it-works pages, and development concepts.
Why use it?
It turns complex ideas into one visual page with connected notes, arrows, boxes, and icons.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the illustration plugin — 2 skills shipped together

Good fit Use it for system explainers, architecture diagrams, product walkthroughs, how-it-works pages, and development concepts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add stevengonsalvez/agents-in-a-box
Claude Code
/plugin install illustration

Made for: Claude Code.

Or install illustration, the plugin that ships this one along with the rest of its 2 skills.

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 illustration:popa

README.md
[![agentmods](https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/popa/github.svg)](https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/popa)
Your own site
<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/popa"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/popa/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 illustration:popa

Your own site · 80×15
<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/popa"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/popa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 85 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 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 $0.00085 $0.00830
Opus 5 $0.00043 $0.00415
Sonnet 5 $0.00017 $0.00166
Haiku 4.5 $0.00009 $0.00083

Measured 11d ago against content hash 7d1182cd75d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

illustration:popa 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.

plugins/illustration/skills/popa/SKILL.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

illustration:popa — intricate sketchnote blob

Generate intricate hand-drawn sketchnotes starring Popa: a pink round blob with a green sprout and a notepad. Popa turns a concept, flow, or system into one busy, packed, readable sketchnote on a soft pastel scene — a banner, many linked boxes/notes/arrows/icons, Popa scribbling in the middle — lots of scribblings in the same note, but every word legible.

Read first

  1. ${CLAUDE_PLUGIN_ROOT}/references/workflow-engine.md — the shared digest → shot list → generate → QA → deliver process.
  2. ${CLAUDE_PLUGIN_ROOT}/references/composition-patterns.md — structure types, format presets, the likeness rule.
  3. references/popa-ip.md — Popa's anchors, personality, the notepad gag, forbidden moves.
  4. references/popa-style-dna.md — the intricate-sketchnote visual law (incl. the text-integrity rule).
  5. references/prompt-template.md — the generation prompt template.
  6. references/qa-checklist.md — pass/fail and iteration.
  7. assets/popa-ref/ — Popa's renders, passed as the likeness reference on every generation (mandatory).
  8. assets/examples/ — calibration only; never copy these compositions.

Core positioning

The goal is to turn a topic — a process, system, argument, or set of features — into one intricate hand-drawn sketchnote: a banner, many small linked ideas in boxes/clouds/tags, arrows and spot icons, with Popa hosting the action. Busy and packed ("lots of scribblings in the same note"), but with clear hierarchy and legible text — no gibberish, ever. Popa is earnest and deadpan; the cuteness is the setup, the situation is the punchline. Popa hosts the note, never just decorates it.

Workflow (engine + Popa specifics)

Follow the five shared steps. Popa specifics:

  • Likeness is mandatory: pass assets/popa-ref/popa_square.png (and tiny_popa2.png for the notepad pose) into the backend with "this is Popa; draw THIS exact character — chubby pear body, green sprout, glossy eyes, rosy cheeks — translated into crude hand-drawn pen line art; do not copy the reference's 3D style or background."
  • Intricate density: pack the page with many linked boxes, notes, arrows and icons — busy, not sparse. Big topics can also become a multi-frame series (see composition-patterns).
  • Text integrity (hard rule): decide the exact short labels first and allow ONLY those words in the image; never let the model invent text. If a finished frame has a garbled label, fix it with a text-only edit, not a regenerate. See references/prompt-template.md.
  • The notepad gag: when there's room, one tiny legible line on the notepad. Max one per image.
  • Pastel background: cream by default (or mint / lavender / blush); for a series keep one tone across frames so they tile. Popa is the only saturated element.

Read the full file on GitHub · 39 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. 11d ago First seen · 39 lines · 85 tokens per session scan A 7d1182cd75d4

Subscribe to this mod's changes

illustration:popa is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (23 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 830 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

seedance-antislop

Detect and remove hollow AI filler language, empty superlatives, and vague boosters that degrade Seedance 2.0 prompt quality. Use when a prompt feels generic, over-written, or 'AI-sounding', or when generation output looks bland and needs a quality pass.

Kingdaddy007/my-os · 61 tokens

seedance-audio

Design sound layers, specify dialogue lip-sync, and troubleshoot audio failures for Seedance 2.0 video generation. Covers @Audio1 reference input, multi-character constraints, known failure modes (silent output, desync, audio rewrite bug), and the boundary between Seedance 2.0 video generation and the separate Jimeng…

Kingdaddy007/my-os · 105 tokens

seedance-copyright

Check prompts against Seedance 2.0 content policy, apply safe IP substitutions, and navigate real-person and brand restrictions. Updated with live Feb 2026 enforcement data from Disney, Paramount, MPA, and SAG-AFTRA actions. Use before every generation that involves named characters, franchise IP, celebrity…

Kingdaddy007/my-os · 77 tokens

seedance-characters

Lock character identity, assign @Tag references, and maintain face and hand consistency across multi-character scenes in Seedance 2.0. Covers 360-degree consistency testing and first-frame art direction for image-to-video. Use when a character changes appearance between shots, when building multi-person scenes, or…

Kingdaddy007/my-os · 72 tokens

seedance-lighting

Specify lighting, atmosphere, and light transitions for Seedance 2.0 prompts using named light sources, core parameters, and atmosphere contracts. Use when the scene needs a specific mood, time of day, or lighting style, or when lighting is flat, inconsistent across shots, or clipping.

Kingdaddy007/my-os · 63 tokens

seedance-motion

Control motion timing, beat density, action choreography, and sequential video extension chains for Seedance 2.0. Covers fight-scene physics, per-shot motion contracts, and multi-clip continuation techniques. Use when motion is too fast, too slow, or jittery, when choreographing action sequences, or when extending a…

Kingdaddy007/my-os · 75 tokens