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.
npx agentmods add skills/nullhack/temple8/design-visual-assetnpx skills add nullhack/temple8 --skill design-visual-assetgit clone --depth 1 https://github.com/nullhack/temple8What 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 | $0.00034 | $0.00430 |
| Opus 5 | $0.00017 | $0.00215 |
| Sonnet 5 | $0.00007 | $0.00086 |
| Haiku 4.5 | $0.00003 | $0.00043 |
Grade A, and why
design-visual-asset 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 2d 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.
What it actually says
Design Visual Asset
- Load [[design/asset-design]], [[design/visual-design]], [[design/accessibility]] — the per-use-case asset inventory, the visual-design levers (hierarchy, contrast, typography), and the accessibility floors every asset must meet.
- Identify the asset + where it lives — social card (1280×640, open-graph previews), README banner (wide, dark-mode-aware), logo/avatar (square, reads at 32–64 px), favicon (square, reads at 16 px). Compose for that context, not for a generic brand system.
- Establish hierarchy with the four levers — size, weight, position, spacing — so the user reads the name first, the intent second, the mark third. Apply parsimony: one mark, generous whitespace, one accent; the dev-branding norm is restraint.
- Author the asset as self-contained SVG: presentation attributes (no inline
<style>hosts strip), no external<use href>or web fonts, a squareviewBoxwith padding, strokes converted to filled paths for production, metadata stripped. - Make it accessible: give the SVG an accessible name (
<title>+aria-labelledby, orrole="img"+aria-label); meet WCAG 2.2 contrast floors against every background it will appear on; pair color with a shape or label so it survives color-blind + dark-mode. - Provide a dark-surface variant where the asset appears on a theme-aware surface (README, GitHub), OR design a monochrome mark on a transparent background that holds on both.
- Verify legibility at the shown size for the avatar (32–64 px) and favicon (16 px) only — simplify the mark if a thin stroke vanishes. Export PNG /
.icoonly where a target demands it; the SVG is the source.
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.
- 2d ago First seen · 15 lines · 34 tokens per session scan A cf6d62464b25
design-visual-asset is a skill published in the GitHub repository nullhack/temple8 (11 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 430 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
create-playwright
Record a browser-session demo (MP4) using Playwright via a replay-first compile pipeline. A YAML spec drives the driver script, the recording, and the ElevenLabs voiceover — mirrors create-vhs for browser flows.
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器，或扫描本机 CDP 端口，用于远程调试与多工具共享浏览器实例。.
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.