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 mike-coulbourn/claude-vibes --skill interview-megit clone --depth 1 https://github.com/mike-coulbourn/claude-vibesWrote 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/mike-coulbourn/claude-vibes/interview-me)<a href="https://agentmods.dev/skills/mike-coulbourn/claude-vibes/interview-me"><img src="https://agentmods.dev/badge/skills/mike-coulbourn/claude-vibes/interview-me/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/mike-coulbourn/claude-vibes/interview-me"><img src="https://agentmods.dev/badge/skills/mike-coulbourn/claude-vibes/interview-me.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 | $0.00082 | $0.00812 |
| Opus 5.5 | $0.00033 | $0.00325 |
| Sonnet 5.5 | $0.00016 | $0.00162 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
interview-me 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Me
Core Behavior
Interview the user relentlessly, one question at a time, until the topic is understood well enough to summarize, document, decide, plan, or create the requested follow-on artifact.
Use AskUserQuestion for every interview question. Do not ask interview questions as plain chat when AskUserQuestion is available.
If AskUserQuestion is unavailable, stop and say the skill requires that tool for the interview experience. Do not continue the interview with plain-text questions unless the user explicitly asks to proceed without the tool.
Question Format
For each interview step:
- Ask exactly one question through
AskUserQuestion. - Use a short header, 12 characters or fewer.
- Provide 2-3 mutually exclusive answer options.
- Put the recommended option first and suffix its label with
(Recommended). - Make the recommended option a real proposed answer, not a vague placeholder.
- Let the tool's free-form
Otherpath handle nuance when the options do not fit. - Keep the visible question concise, but include enough context for the user to answer quickly.
Interview Method
Before asking, decide whether the answer can be discovered from available artifacts, repos, docs, previous messages, diagnostics, or uploaded files. If it can, inspect the source instead of asking the user.
Walk the decision tree branch by branch:
- Establish the root definition of the topic.
- Identify the purpose of the interview and the desired end artifact or decision.
- Capture the audience, stakeholders, users, or affected parties.
- Surface the user's goals, constraints, preferences, and non-negotiables.
- Map the current state, history, and why prior choices were made.
- Identify edge cases, exceptions, risks, objections, and failure modes.
- Resolve dependencies between answers before moving to downstream branches.
- Test the emerging model by proposing concise summaries and asking the user to correct them.
- Continue until new questions are producing little new information or the user stops the interview.
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.
- 1mo ago First seen · 78 lines · 82 tokens per session scan A 28d60a2028af
interview-me is a skill published in the GitHub repository mike-coulbourn/claude-vibes (44 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 812 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 2026-09-22.
Other skills, from other repositories
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Invoke with /i-have-adhd; stays on until "stop adhd mode".
service-desk
Runs the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets…
collaboration-platform-administration
Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal…
onboarding-and-offboarding
Designs the joining and leaving experience — first-day readiness, ramp to productivity, knowledge capture, and clean exits. Use this to design or fix onboarding, shorten time to productivity, structure a leaver process, capture knowledge before someone leaves, or coordinate the access and asset steps around a joiner…
mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
phx-mix-compression
Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.