ryanb/dotfiles is a collection of command-line configuration files for macOS, centered on Zsh and related tools such as Git, Ruby, Rails, and IRB. It is for developers who want to customize their terminal with commands, completions, prompts, and fuzzy-finding workflows. Its catalogue skills and plugin provide coding-agent workflows built into the same setup.
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 ryanb/dotfiles --skill interviewgit clone --depth 1 https://github.com/ryanb/dotfilesWrote 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/ryanb/dotfiles/interview)<a href="https://agentmods.dev/skills/ryanb/dotfiles/interview"><img src="https://agentmods.dev/badge/skills/ryanb/dotfiles/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/ryanb/dotfiles/interview"><img src="https://agentmods.dev/badge/skills/ryanb/dotfiles/interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.00425 |
| Opus 5.5 | $0.00027 | $0.00170 |
| Sonnet 5.5 | $0.00013 | $0.00085 |
| Haiku 4.5 | $0.00007 | $0.00042 |
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 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.
What it actually says
Interview
Interview the user relentlessly about every aspect of this plan or design until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one at a time.
Rules for questions
- One question at a time. Never bundle multiple questions into a single turn. Ask, wait for the answer, then ask the next.
- Don't move on until the current question is answered. If the user asks for clarification, adds to an earlier answer, or replies without choosing, answer them and re-ask the same question under the same number, revised if needed. A reply doesn't have to contain a new question.
- Number questions in strict sequence. A question keeps its number until it's answered; the next question takes the next integer.
- Always present a numbered list of multiple-choice answers. Every question must offer concrete options as a plain numbered list (1, 2, 3, …). The user can always free-write a different answer, so there's no need for an explicit "Other" option.
- Always give a recommendation. After the options, state which option you recommend and why, in one line.
- Explore before asking. If a question can be answered by exploring the codebase, do that instead of asking.
Format every question like this:
<The single question>
1. <Option one>
2. <Option two>
3. <Option three>
Recommendation: <option number and a one-line reason>
Keep going until the design tree is resolved — scope, behavior, edge cases, data model, UI/UX, integrations, permissions, and any open questions are all settled.
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 Changed · +1 lines 7dc985a790fb
- 29d ago Changed · +1 lines d82788d35c73
- 1mo ago First seen · 31 lines · 67 tokens per session scan A 23c21a7d77b4
interview is a skill published in the GitHub repository ryanb/dotfiles (2,400 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 425 once invoked, about $0.0003 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 2026-08-30.
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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…