Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add swt-labs/vibe-better-with-claude-code-vbw/plugin install vbwWrote 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/swt-labs/vibe-better-with-claude-code-vbw/interview)<a href="https://agentmods.dev/skills/swt-labs/vibe-better-with-claude-code-vbw/interview"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/interview/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/swt-labs/vibe-better-with-claude-code-vbw/interview"><img src="https://agentmods.dev/badge/skills/swt-labs/vibe-better-with-claude-code-vbw/interview.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 | $0.00059 | $0.01341 |
| Opus 5.5 | $0.00024 | $0.00536 |
| Sonnet 5.5 | $0.00012 | $0.00268 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" interview 2>&1 || true
"${CLAUDE_PLUGIN_ROOT}/bin/vbw" legacy review 2>&1 || true
Answers so far above. Once kept, write every later message at the user's level, explanation depth and involvement.
Router calls this when profile.ask is true: after mapping (existing code), before any spec or convert work. Ask with AskUserQuestion, one question at a time, plain words. Skip the answers profile already holds: resume at first unanswered, named by profile.pending (level, depth, involvement, then keep). vbw interview shows same state.
The three fixed questions
Record each answer at once; an interrupted interview loses nothing. Offer exactly these options, this order, no others: never reorder or mark one Recommended, whatever earlier answers suggest (user's own facts, not a choice VBW advises).
- "Hello, Human! Welcome to VBW. Let me interview you real quick to better adapt to you. What is your level of proficiency?"
Options: never; small scripts or no-code; professionally; senior engineer.
Record:
vbw interview set level "<option>". - "How should I explain things?"
Options: plain words; plain with technical terms explained; technical and brief.
Record:
vbw interview set depth "<option>". - "How involved do you want to be in technical decisions?"
Options: decide and tell me; options with a recommendation; I make the calls.
Record:
vbw interview set involvement "<option>".
Kernel refuses other values and names allowed ones. On refusal or an answer fitting no option (free text, "Other"): never record it; ask again, same question, same options. Never guess nearest option.
The old VBW 1 folder
One extra step, right after the level answer, before any other question. Review above. "legacy": false (no folder) or asked true (a choice is recorded): skip it and say nothing; it is asked once.
Else show it at the user's level and depth: how much was finished, when last used, whether plans still match the code, any work half done. Never guess or change the kernel's numbers, recommendation or reasons. Say any notes (what could not be read); never recommend converting what could not be read.
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.
- today First seen · 78 lines · 59 tokens per session scan A 8562daf651f6
interview is a skill published in the GitHub repository swt-labs/vibe-better-with-claude-code-vbw (85 stars, last pushed today), licensed MIT. It adds 59 tokens to every session and 1,341 once invoked, about $0.0002 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 2026-10-22.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…