finance-automation-portfolio: Skill for Claude Code

.claude/skills/brand-graphics/SKILL.md

brand-graphics is a skill for Claude Code from sophonfinance-wq/finance-automation-portfolio. It costs 52 tokens per session (628 once invoked), scanned A, original, MIT.

A tool for creating technical diagrams, LinkedIn graphics, and system animations in a consistent light engineering style. It uses hand-built SVG graphics, a web format for sharp, editable diagrams, when labels need to be accurate.

In plain words
What is it for?
Use it to create architecture diagrams, documentation visuals, branded social graphics, and system GIFs with controlled text, colors, and layout.
Why use it?
It keeps diagrams readable and prevents small labels from being distorted by image-generation systems. It also provides a shared visual language for technical and professional materials.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sophonfinance-wq/finance-automation-portfolio's own configuration. It tells Claude Code how to work on finance-automation-portfolio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything finance-automation-portfolio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sophonfinance-wq/finance-automation-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sophonfinance-wq/finance-automation-portfolio/main/.claude/skills/brand-graphics/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sophonfinance-wq/finance-automation-portfolio

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 brand-graphics

README.md
[![agentmods](https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/brand-graphics/github.svg)](https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/brand-graphics)
Your own site
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/brand-graphics"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/brand-graphics/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 brand-graphics

Your own site · 80×15
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/brand-graphics"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/brand-graphics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 628 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 $0.00052 $0.00628
Opus 5.5 $0.00021 $0.00251
Sonnet 5.5 $0.00010 $0.00126
Haiku 4.5 $0.00005 $0.00063

Measured 2mo ago against content hash cb98b565e3ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brand-graphics 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 2mo 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.

.claude/skills/brand-graphics/SKILL.md · 29 lines

What it actually says

Sophon Brand Graphics

Palette

Navy #0f2a5c (ink/headers) - blue #2563eb (accent) - sky #00a8ff - slate #5b6b84 (muted) - light ground #f6f8fb with faint 30px grid #eef2f8 - green #2f6b4f/#15803d (pass) - amber #c8912f/#d29922 (review) - red #c0392b (break). Wordmark: Georgia serif "SOPHON" + letterspaced sans "FINANCE SYSTEMS - sophonfinance.com".

Hard rules learned the hard way

  • Light background, dark text for LinkedIn/professional audiences.
  • Never use AI image models for diagrams with small text — they garble labels ("Manual scove and"). Hand-build as HTML/SVG; every character controlled. Higgsfield (nano_banana_pro) is OK only for texture/hero art, and output text must be proofread.
  • CPA-readable labels: no control-theory jargon (no Sigma comparator symbols) — say "DOES IT TIE OUT?", "TIES / BREAKS / JUDGMENT", "FIX FROM SOURCE".
  • Verify text fits its shape; add an auto-shrink pass or measure before shipping. Strip <script> from SVGs destined for GitHub (sanitized there).

Render pipeline (this container)

/opt/pw-browsers/chromium-1194/chrome-linux/chrome --headless=new --no-sandbox --hide-scrollbars \
  --window-size=WxH --force-device-scale-factor=2 --default-background-color=FFFFFFFF \
  --screenshot=out.png file:///path/page.html

Read the PNG back and visually verify before delivering. Fonts: Liberation family at /usr/share/fonts/truetype/liberation/ (Sans/Sans-Bold/Mono map to segoeui/seguisb/consola).

System GIFs

assets/make_system_gifs.py — scripted terminal-frame renderer (PIL, 2x supersampled). Add a SYSTEMS entry (authentic code + real output only), then python make_system_gifs.py <key>. Has Linux font fallback + a loop icon.

Existing assets

assets/flows/*.svg (numbered-card template), assets/architecture.svg, assets/flows/self-healing-close-loop.svg (CPA loop diagram), docs/assets/self-healing-loop.svg (site copy).

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. 2mo ago First seen · 29 lines · 52 tokens per session scan A cb98b565e3ed

Subscribe to this mod's changes

brand-graphics is a skill published in the GitHub repository sophonfinance-wq/finance-automation-portfolio (16 stars, last pushed 27d ago), licensed MIT. It adds 52 tokens to every session and 628 once invoked, about $0.0002 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 2026-08-30.

Related

brand-graphics compared with skills from other repositories

brand-graphics next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
brand-graphicssophonfinance-wq/finance-automation-portfolioSkill1627d agoMITA52Claude Code
cocoindex-diagramscocoindex-io/cocoindexSkill12ktodayApache-2.0A124Claude Code, Codex
cli-commandComposioHQ/composioSkill31ktodayMITA76Claude Code, Codex
dashboard-designmckinsey/vizroSkill3.8ktodayApache-2.0A71Claude Code
dstack-prototypingdstackai/dstackSkill2.3k2d agoMPL-2.0A80Claude Code, Codex
designing-vizro-layoutsmckinsey/vizroSkill3.8ktodayApache-2.0A58Claude Code
diagram-designvstorm-co/pydantic-deepagentsSkill1.1k9d agoMITA16Claude Code, Codex