Borrowing it
Nothing to install: this file belongs to anteprojector/sidecar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anteprojector/sidecar/main/.claude/skills/refresh-brand-assets/SKILL.mdgit clone --depth 1 https://github.com/anteprojector/sidecarWrote 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.
[](https://agentmods.dev/skills/anteprojector/sidecar/refresh-brand-assets)<a href="https://agentmods.dev/skills/anteprojector/sidecar/refresh-brand-assets"><img src="https://agentmods.dev/badge/skills/anteprojector/sidecar/refresh-brand-assets/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.
<a href="https://agentmods.dev/skills/anteprojector/sidecar/refresh-brand-assets"><img src="https://agentmods.dev/badge/skills/anteprojector/sidecar/refresh-brand-assets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00953 |
| Opus 5.5 | $0.00026 | $0.00381 |
| Sonnet 5.5 | $0.00013 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
refresh-brand-assets 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refreshing generated brand assets
Some of this repo's user-facing text is baked into images. Editing the
source copy is only half the change; the rendered asset keeps showing the old
wording until it is re-rendered. grep cannot catch this, because by then the
words are pixels.
This bit once: the v0.9.0 rename to sidecarsync updated every markdown and
HTML file, and og.png still told every Slack and Twitter unfurl to
npm i -g @projectors/sidecar. Unfurl caches hold that for weeks.
What is generated, and from what
| Asset | Source | Regenerate with |
|---|---|---|
packages/marketing/site/assets/og.png |
packages/marketing/scripts/og-card.html |
bun run --cwd packages/marketing og:render |
packages/marketing/site/assets/favicon.{png,svg} |
scripts/make-favicon.py |
bun run --cwd packages/marketing favicon |
packages/marketing/branding/readme-hero.svg |
scripts/make-readme-hero-*.{py,mjs} |
bun run --cwd packages/marketing readme-hero |
packages/sidecar/dist/cli.js |
packages/sidecar/src/** |
bun run build (CI diffs this) |
Only og.png carries text today. The logo, hero, and favicon are pure vector
art with no text elements, so copy changes never affect them — but a palette
or logo change does.
When to re-render og.png
Any change to the install command (including a package rename), the
tagline, the site URL, the wordmark, or the yellow colorway. The card draws
its own copy from og-card.html, so if you edited that file, re-render.
How
bun run --cwd packages/marketing og:render
That is scripts/make-og.mjs. It boots the repo's own static server, drives
an installed Chrome headlessly over the DevTools protocol, and writes the PNG.
Zero dependencies — no Playwright, no Puppeteer, no rasterizer in the tree.
Then confirm the result by looking at it (read the PNG as an image), not by trusting the exit code. Check the install command, wordmark, and URL.
If Chrome is somewhere unusual: CHROME=/path/to/chrome bun run --cwd packages/marketing og:render.
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.
- 2mo ago First seen · 84 lines · 65 tokens per session scan A cd6852a594dc
refresh-brand-assets is a skill published in the GitHub repository anteprojector/sidecar (5 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 953 once invoked, about $0.0003 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 2026-08-31.
refresh-brand-assets compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| refresh-brand-assetsanteprojector/sidecar | Skill | 5 | 2mo ago | MIT | A | 65 | Claude Code |
| verifybuttjer/n8n-decanter | Skill | 2 | 3d ago | MIT | A | 0 | Claude Code |
| design-qacoo1white/cool-workflow | Skill | 2 | 2d ago | BSD-2-Clause | A | 61 | Claude Code, Codex |
| housekeepingbuttjer/n8n-decanter | Skill | 2 | 3d ago | MIT | A | 0 | Claude Code |
| design-reviewwolfenazz/YzPzCode | Skill | 20 | yesterday | Apache-2.0 | A | 28 | Claude Code, Codex |
| accessibilityworkstream-labs/workstreams | Skill | 78 | 6mo ago | none | A | 54 | Claude Code, Codex |
| author-contributionsworkstream-labs/workstreams | Skill | 78 | 6mo ago | none | A | 68 | Claude Code, Codex |