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 skills add giang6283623/minimal-vibe-coding-kit --skill wait-whatgit clone --depth 1 https://github.com/giang6283623/minimal-vibe-coding-kitWrote 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/giang6283623/minimal-vibe-coding-kit/wait-what)<a href="https://agentmods.dev/skills/giang6283623/minimal-vibe-coding-kit/wait-what"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/wait-what/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/giang6283623/minimal-vibe-coding-kit/wait-what"><img src="https://agentmods.dev/badge/skills/giang6283623/minimal-vibe-coding-kit/wait-what.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 | $0.00030 | $0.00597 |
| Opus 5 | $0.00015 | $0.00298 |
| Sonnet 5 | $0.00006 | $0.00119 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
wait-what 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 12d 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
Wait What
The user is saying: comprehension failed. This is a repair of the listener's state, not a request for shorter text and not a request for new work. Re-pitch the previous message immediately. Text after the invocation names the part that lost the user; no text means re-pitch the whole previous message.
Rules for the re-pitch:
- Diagnose first, silently: what failed is usually one of a missing premise, an undefined term, a skipped step, the wrong altitude (too abstract or too deep in detail), or a buried outcome. Repair that specific failure. An agent that hears "be brief" writes telegrams; an agent that hears "you lost me" backs up and explains.
- Reply in the user's conversation language (English, Vietnamese, Chinese, or any other). Never switch to English to explain, and never mix registers mid-reply.
- Plain-language register in every language: lead with the outcome, short sentences, one idea per sentence, active voice, concrete verbs, known information before new information, and define each necessary term at first use. Only when the reply language is English, also hold ASD-STE100-style simplicity: one meaning per word, no synonym rotation. The target is shorter and clearer, never shorter and blunter.
- Use the project's own vocabulary: the glossary file named in
backbone.ymlproject.contextwhen present (in this kit:.vibekit/docs/CONTEXT.md). Without a glossary, use the exact names frombackbone.ymland the code, and offer in one line to scaffoldCONTEXT.mdfrom.vibekit/docs/templates/CONTEXT_TEMPLATE.md. Never invent or localize project terms that the glossary does not define. - Quote code identifiers, commands, file paths, and error text verbatim in every language; never translate, paraphrase, or rename them.
- Zero new work: same facts, same decisions, same state as the original message. No tool calls, no edits, no new conclusions. If re-explaining exposes an error in the original message, say so in one line and stop; the fix is a new task the user must ask for.
- The register applies to this re-pitch, not to the rest of the session; standing style comes from the project's writing rules.
- End with one short line naming the part most likely still unclear, so the user can aim the next "wait" precisely.
Done when: the re-pitch restores the missing premise in the user's language, is shorter and clearer than the original, and every project term comes from the glossary or the code, not invention.
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.
- 12d ago First seen · 24 lines · 30 tokens per session scan A 5c47a0483f59
wait-what is a skill published in the GitHub repository giang6283623/minimal-vibe-coding-kit (23 stars, last pushed 15d ago), licensed MIT. It adds 30 tokens to every session and 597 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…