figure-audit

figure-audit is a skill for Claude Code from slogsdon/skills-design. It costs 109 tokens per session (794 once invoked), scanned A, original, MIT.

A review guide that decides whether an article genuinely needs a figure, such as a diagram or chart. It uses five figure types and requires evidence for each one.

In plain words
What is it for?
Use it to assess articles before commissioning diagrams or charts. It can evaluate dimensioned diagrams, cycles, record charts, decision trees, and explanatory diagrams against stated requirements.
Why use it?
It helps prevent decorative figures that merely repeat the article's point or invent unsupported data. Its default is to recommend no figure when one adds no real value.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills-design plugin — 19 skills shipped together

Good fit Use it to assess articles before commissioning diagrams or charts. It can evaluate dimensioned diagrams, cycles, record charts, decision trees, and explanatory diagrams against stated requirements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/slogsdon/skills-design/figure-audit
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 slogsdon/skills-design --skill figure-audit
Clone the repo
git clone --depth 1 https://github.com/slogsdon/skills-design

Made for: Claude Code.

Or install skills-design, the plugin that ships this one along with the rest of its 19 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 figure-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/slogsdon/skills-design/figure-audit"><img src="https://agentmods.dev/badge/skills/slogsdon/skills-design/figure-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 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 $0.00109 $0.00794
Opus 5 $0.00055 $0.00397
Sonnet 5 $0.00022 $0.00159
Haiku 4.5 $0.00011 $0.00079

Measured 10d ago against content hash dd6793a2c9af, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

figure-audit 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 10d 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.

skills/figure-audit/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: /figure-audit [article path]

Answer whether a figure earns its place, applying the standard that most articles should get none — the value is in the rejections, not the approvals.

Don't: invent the data a figure would need; if the article does not contain the numbers, the verdict is not additive, full stop. Don't approve a figure that restates the thesis in boxes — that is the exact failure this guards against. Don't audit several articles in one agent; it starts pattern-matching the second against the first and stops reading.

The standard

If the page is no worse without the figure, cut the figure.

Prefer none. Reaching for a figure to fill space is the failure mode.

The taxonomy

A figure may ONLY be one of these five types, and ONLY if it meets its entry requirement.

Figure Use it for REQUIRES
Dimensioned diagram A claim about proportion, or where a line sits Two regions and a measured split you can defend
Cycle A process with a genuine return edge Three or more stages AND a real loop back
Record chart A claim about the author's own history or data A file it reconciles to, named in the caption
Detail Clarifying one step of an assembly A step that is actually unclear without it
Footed table Anything with numbers, including pricing Figures that add up, shown adding up

Hard limits: max one figure per article, max three callouts per figure. Zero figures is a perfectly good answer.

Rules

  1. No invented data. groundedIn must quote or cite something actually in the article.
  2. Record chart needs a real file it reconciles to. Do not claim reconciliation you cannot verify.
  3. Cycle needs a genuine return edge. A linear process with steps is not a cycle.
  4. Dimensioned diagram needs a defensible measured split — an explicit percentage or ratio stated in the article. A vibes-based split is not defensible.
  5. Prefer none.

Steps

  1. Read the project's DESIGN.md figure section — if it defines a different taxonomy, that file wins over the table above.
  2. Read the article in full. Not the intro, not a grep.
  3. Test each of the five types against its entry requirement, in order. Stop at the first that genuinely passes.
  4. Return the verdict.

Read the full file on GitHub · 63 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. 10d ago First seen · 63 lines · 109 tokens per session scan A dd6793a2c9af

Subscribe to this mod's changes

figure-audit is a skill published in the GitHub repository slogsdon/skills-design (3 stars, last pushed 26d ago), licensed MIT. It adds 109 tokens to every session and 794 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

self-media-short-video

A planning and production guide for vertical short videos on platforms such as TikTok, Xiaohongshu, and WeChat Channels.

yanhua1010/self-media-content-workflow · 118 tokens

self-media-content-delivery

A file-based process for saving, versioning, checking, and packaging completed social-media content.

yanhua1010/self-media-content-workflow · 103 tokens

self-media-trend-radar

A research guide for tracking public trends, search terms, popular content, competitors, and audience questions. It turns that research into original content ideas supported by evidence.

yanhua1010/self-media-content-workflow · 96 tokens

component-family-consistency

Buttons, inputs, pills, badges, calendars, and other interactive components form a visual family — they share the same border-radius, colour logic, shadow scale, border style, and spacing rhythm. Inconsistency between them breaks the sense of a coherent product. Use when building or reviewing a component library…

dembrandt/dembrandt-skills · 76 tokens

x-marketing

Plan, draft, audit, and publish posts and threads for X (Twitter). Use when the user wants to write a single tweet or an auto-numbered thread, build a long-form tweetstorm, remove AI tells from a draft, reverse-engineer the hook from a viral tweet, draft a reply or quote tweet, or plan a week of X content. Tweets and…

sergebulaev/x-skills · 117 tokens

paint

Paint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audit. Anti-AI-slop design pipeline. Adapts to Web, Android (Compose), Apple (SwiftUI).

AThevon/genjutsu · 46 tokens