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/kbashar/myagentskills/visual-docsnpx skills add kBashar/myagentskills --skill visual-docsgit clone --depth 1 https://github.com/kBashar/myagentskillsWhat 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 | $0.00087 | $0.01200 |
| Opus 5 | $0.00044 | $0.00600 |
| Sonnet 5 | $0.00017 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
visual-docs 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visual Docs
Overview
Analysis and explanation docs land better as a visual, browsable HTML page, not just markdown. This skill carries a specific visual identity — a "field-survey / blueprint schematic": monospace-forward, hairline borders, sharp corners, a faint plotted-grid ground, one bold accent, muted role hues. Adapt the accent and role hues to each subject rather than copying verbatim.
Core principle: pair the written analysis with a page someone can scan, where every structural device (numbering, swatches, dividers, labels) encodes something true about the content — never decoration.
When to Use
- "Explain how X works", "document/analyze this system", "write a runbook / report / design doc"
- Any time the deliverable is a document AND a visual would read more clearly than prose
- You're about to hand over a checklist, comparison, architecture map, or pipeline
Not for: throwaway answers, code comments, or when the user explicitly asks for plain markdown/text.
Bundled files
Both live next to this file. This skill is self-contained — it depends on no other skill.
page-craft.md— the craft floor for any page: treatment calibration, theme tokens, typography, layout, copy, build hygiene, the AI-default looks to avoid, and a pre-delivery checklist.design-system.md— the blueprint-schematic visual identity: exact palette, role hues, type stack, structural devices.
Process
- Read
page-craft.md— the standards every page here must clear. - Read
design-system.mdfor the exact palette, type stack, and layout devices. Build from its tokens. - Adapt to the subject — assign the ONE bold accent to the subject's conceptual crux; map role hues to the subject's own categories. Don't reuse the reference hues verbatim.
- Build self-contained HTML — inline CSS/JS, no external assets; both light + dark via
:roottokens +prefers-color-schemeANDdata-themeoverrides; responsive withoverflow-x:autoon wide content;<title>+ emoji favicon. - Deliver the local file — write a standalone
.html(full<!DOCTYPE>) into the repo (e.g.docs/) so it lives with the code, give the user the path, and stop. The local file is the whole deliverable; publishing is a separate request, never a bonus you add on your own. - Publish only when the user asked for a hosted copy. The predicate is an explicit request in their words — "publish it", "host it", "give me a link", "share it", "put it on claude.ai". Anything short of that (a page-publishing tool being available, the page looking shareable, the user seeming likely to want a link) means do not publish; offer the option in one sentence instead. When they do ask: hosts typically wrap their own
<head>/<body>, so publish a body-fragment copy — no<!DOCTYPE>/<html>/<head>/<body>tags, keeping the<style>, content, and<script>. Drop any custom theme-toggle button from the fragment — the host supplies its own toggle, stampingdata-themeon the root, which the tokens already handle. Pass an emoji favicon and a one-line description, then report both the local path and the URL. - Verify — run the checklist at the end of
page-craft.md: both themes legible, toggle wins over OS preference, no horizontal body scroll, no silent font fallback, keyboard focus visible.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 58 lines · 87 tokens per session scan A 3be1719ca342
visual-docs is a skill published in the GitHub repository kBashar/myagentskills (2 stars, last pushed 6d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,200 once invoked, about $0.0004 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…