agentmods.dev

figure.create_description

figure.create_description is a skill for Claude Code from gpsaggese/helpers. It costs 15 tokens per session (362 once invoked), scanned A, original, Apache-2.0.

A writing task that turns a diagram, image, or described concept into a concise explanation for a technical book.

In plain words
What is it for?
Use it to describe panels, flows, axes, layers, labels, and other visual parts, and to suggest optional clarity improvements.
Why use it?
It gives readers who lack background context a self-contained account of the diagram's layout, purpose, and main lesson.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

not rated 158repo +1 today A scan 15 tokens original Apache-2.0

Good fit Use it to describe panels, flows, axes, layers, labels, and other visual parts, and to suggest optional clarity improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gpsaggese/helpers/figure.create_description
View source ↗ gpsaggese/helpers
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.

Any agent
npx skills add gpsaggese/helpers --skill figure.create_description
Clone the repo
git clone --depth 1 https://github.com/gpsaggese/helpers

Made for: Claude Code.

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 figure.create_description

README.md
[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/figure.create_description/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/figure.create_description)
Your own site
<a href="https://agentmods.dev/skills/gpsaggese/helpers/figure.create_description"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/figure.create_description/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 figure.create_description

Your own site · 80×15
<a href="https://agentmods.dev/skills/gpsaggese/helpers/figure.create_description"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/figure.create_description.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 362 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 $0.00015 $0.00362
Opus 5.5 $0.00006 $0.00145
Sonnet 5.5 $0.00003 $0.00072
Haiku 4.5 $0.00002 $0.00036

Measured yesterday against content hash 89b9e7198e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

figure.create_description 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 yesterday.

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.

.claude/skills/figure.create_description/SKILL.md · 39 lines

What it actually says

Role

  • You are a technical illustrator writing figure descriptions for a published technical book
  • Your descriptions appear as standalone callout boxes or chapter openers, so they must be self-contained and immediately useful to a reader who may not yet have read the surrounding text

Input

  • You will receive one of:
    1. An image: a diagram, chart, or illustration
    2. A concept or scenario: described in plain text

Task

  • Produce a concise figure description that covers:
    1. Overview: one sentence stating what the diagram shows and why it matters
    2. Structure: walk through the visual layout (e.g. panels, flow, axes, layers) in reading order, naming each component and its role
    3. Key insight: the single most important takeaway a reader should retain
    4. Visual notes (optional): flag any enhancements that would improve clarity (e.g. color coding, callout labels, a legend, or a simpler layout)

Constraints

  • Write for a technical but non-specialist audience
  • Use present tense and active voice
  • Keep the full description under 200 words unless the diagram is unusually complex
  • Do not invent details that are not present in the input

Verification

  • Confirm the description covers Overview, Structure, and Key insight
  • Confirm the description is under 200 words, or the diagram justifies more
  • Confirm every detail traces back to the input image or concept
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. yesterday First seen · 39 lines · 15 tokens per session scan A 89b9e7198e66

Subscribe to this mod's changes

figure.create_description is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 362 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-06.

Creative and mediaWriting and docs
Related

figure.create_description compared with skills from other repositories

figure.create_description next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
figure.create_descriptiongpsaggese/helpersSkill158todayApache-2.0A15Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex