agentmods.dev

brand-export

A command that converts an SVG asset into a PNG image. SVG is a shape-based format, while PNG is a pixel-based format commonly used for sharing or displaying images.

In plain words
What is it for?
Use it to rasterize a generated SVG from output/ at a chosen width for use as a PNG.
Why use it?
It lets you keep editable SVG files in the repository and create PNG copies only when needed. It can use an installed image library or an operating-system tool.

Command

5 1mo ago A scan 29 tokens original MIT
View the source file localplugins/plugins
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.

agentmods
npx agentmods add commands/localplugins/plugins/brand-export
Clone the repo
git clone --depth 1 https://github.com/localplugins/plugins
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00490
Opus 5 $0.00015 $0.00245
Sonnet 5 $0.00006 $0.00098
Haiku 4.5 $0.00003 $0.00049

Measured yesterday against content hash 28180c6ab2ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brand-export 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.

brand-forge/commands/brand-export.md · 46 lines

What it actually says

/brand-export

Rasterize a vector asset to PNG on demand. brand-forge ships SVG (scalable, editable, zero-permission); PNG copies are produced here when you need them. No PNGs are stored in the repo.

Steps

  1. Pick the source SVG from output/ (ask if not given) and a target width (default 1024).

  2. Try the built-in rasterizer:

    node "${CLAUDE_PLUGIN_ROOT}/lib/rasterize.mjs" output/<name>.svg output/<name>.png <width>

    This uses the optional sharp dependency. If it prints a "needs sharp" message, sharp isn't installed — either npm i sharp in the plugin, or use an OS tool below.

OS-native fallbacks (no dependency)

  • macOS (Quick Look): 
    qlmanage -t -s <width> -o <output-dir> output/<name>.svg   # writes <name>.svg.png
  • Headless Chrome/Chromium (wrap the SVG so it fills the viewport, then screenshot): 
    printf '<!doctype html><style>html,body{margin:0}svg{width:100vw;height:100vh}</style>%s' "$(cat output/<name>.svg)" > /tmp/w.html
"chrome" --headless=new --disable-gpu --force-device-scale-factor=2 \
  --screenshot=output/<name>.png --window-size=<w>,<h> file:///tmp/w.html
  • librsvg: 
    rsvg-convert -w <width> output/<name>.svg -o output/<name>.png

Notes

  • Prefer keeping the SVG as the source of truth; export PNG for platforms that need raster.
  • Fonts render with whatever is installed on the machine doing the rasterization; if a brand font is missing, the declared fallback applies (flag the substitution).
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 · 46 lines · 29 tokens per session scan A 28180c6ab2ec

Subscribe to this mod's changes

brand-export is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 490 once invoked, about $0.0001 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.

Writing and docsbrandingclaude-codeclaude-code-marketplaceclaude-code-pluginscontent-generationdeveloper-tools
Related

Other commands, from other repositories

security-audit-static

Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.

phuryn/pm-skills · 29 tokens

performance-audit-static

Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.

phuryn/pm-skills · 33 tokens

sprint

Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.

phuryn/pm-skills · 15 tokens

analyze-test

Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.

phuryn/pm-skills · 20 tokens

plan-okrs

Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.

phuryn/pm-skills · 17 tokens

write-stories

Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.

phuryn/pm-skills · 20 tokens