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/vthinkdeveloper/vthink-agent-toolkit/html-itnpx skills add vthinkdeveloper/vthink-agent-toolkit --skill html-itgit clone --depth 1 https://github.com/vthinkdeveloper/vthink-agent-toolkitWhat 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 | $0.00121 | $0.02439 |
| Opus 5 | $0.00060 | $0.01220 |
| Sonnet 5 | $0.00024 | $0.00488 |
| Haiku 4.5 | $0.00012 | $0.00244 |
Grade A, and why
html-it 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.
How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
html-it
Render a markdown document as a standalone, self-contained HTML file with embedded CSS — the kind of document the user can open in a browser, screenshot, or share via Slack/email.
See https://claude.com/blog/using-claude-code-the-unreasonable-effectiveness-of-html for the aspirational style reference: rich, scannable, opinionated layout — not a generic markdown→HTML dump. When the source markdown has structure (sections, decisions, tables, status, checklists, before/after), reflect that structure visually with cards, badges, pills, dividers — not just <h2> and <p>.
Workflow
Step 1: Resolve the source file
- If the user passed a path as argument, use it.
- Otherwise, glob for the most recently modified
.mdfile in:~/.claude/plans/- The current working directory's
docs/folder - The current working directory itself
Confirm the chosen file to the user in one line ("Rendering: path/to/file.md") before proceeding. If multiple plausible matches, ask via AskUserQuestion.
Step 2: Read and understand the structure
Read the entire markdown file. Identify the document's logical sections:
- Title / context — usually the H1 + intro paragraph
- Decisions / recommendations — call these out with a card or callout
- Tables — render as styled tables (zebra rows, subtle borders)
- Code blocks / file paths — monospace, light gray background
- Open questions / decisions to confirm — render as a distinct "needs input" block
- Verification / test plan / checklist — render as a styled checklist with checkboxes
- Before/after comparisons — render side-by-side or as a two-column table
- Status / state — render as a colored pill
This is not a literal markdown-to-HTML conversion. You're authoring an HTML document that communicates the same content in a richer form.
Step 3: Apply the project's established style
Use these CSS tokens as your design system. Put the full <style> block inline in <head>:
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.
- yesterday First seen · 161 lines · 121 tokens per session scan A 802a9f0f2476
html-it is a skill published in the GitHub repository vthinkdeveloper/vthink-agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 2,439 once invoked, about $0.0006 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…