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/nweii/agent-stuff/visual-keywordsnpx skills add nweii/agent-stuff --skill visual-keywordsgit clone --depth 1 https://github.com/nweii/agent-stuffWhat 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 | $0.00057 | $0.00965 |
| Opus 5 | $0.00028 | $0.00483 |
| Sonnet 5 | $0.00011 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
visual-keywords 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Keywords
Analyze the provided visual content and generate a dense string of searchable keywords. This is intended to make images and media easier to fuzzy search during recall, not to act as alt text or prose description. Specify the type:
- Aesthetic/Image keywords — For design work, photos, illustrations, UI screenshots
- Font keywords — For typeface specimens, font families, typography examples
For Aesthetic/Image Keywords
Analyze and extract keywords for visual elements, style, composition, and emotional impact.
Analysis Framework
- Subjects/Motifs: Main elements, objects, themes (portrait, landscape, geometric shapes, etc.)
- Mood/Adjectives: Emotions and aesthetics evoked (cheerful, gloomy, elegant, grungy, etc.)
- Medium/Context: Type of visual (photo, illustration, 3D render, graphic design, UI, etc.)
- Style/Genre: Artistic influences, design paradigms (Art Nouveau, brutalist, steampunk, etc.)
- Color Palette: Dominant colors and schemes (pastels, neon, earth tones, monochrome, etc.)
- Composition: Layout, perspective, symmetry, visual flow (closeup, isometric, minimalist, etc.)
- Emotional Impact: Intended feelings (awe, mystery, calm, nostalgia, unease, etc.)
- Details: Settings, techniques, textures, lighting, time period
Output Format
Synthesize into a dense string of keywords using concise, shorthand style. Omit articles, prepositions, and grammatical connectors. Avoid prose or alt-text style descriptions. Focus entirely on maximizing keyword matching for fuzzy search. ~100-150 words per image in a code block.
Example:
majestic dragon craggy cliffside wings outspread tail coiled glowing crystal orb fantasy concept art intricate scales spines horns luminous full moon starry night sky deep blues purples orange accents dramatic cinematic composition close-up head distant body background polished painterly aesthetic atmospheric haze lighting effects highly detailed digital illustration awe power magic wonder adventure
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 · 72 lines · 57 tokens per session scan A 3e63d1bb7b42
visual-keywords is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 14d ago), licensed MIT. It adds 57 tokens to every session and 965 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…