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 naveedharri/benai-skills --skill interview-megit clone --depth 1 https://github.com/naveedharri/benai-skillsWrote 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/naveedharri/benai-skills/interview-me)<a href="https://agentmods.dev/skills/naveedharri/benai-skills/interview-me"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/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/naveedharri/benai-skills/interview-me"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/interview-me.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 | $0.00087 | $0.00641 |
| Opus 5 | $0.00044 | $0.00320 |
| Sonnet 5 | $0.00017 | $0.00128 |
| Haiku 4.5 | $0.00009 | $0.00064 |
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 7d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview Me
Most briefs fail because the missing context is in the user's head and nobody asked for it. This skill pulls it out before any work starts, using the pattern Anthropic recommends: interview one question at a time, prioritising the questions whose answers would change the plan.
Source: A field guide to Claude Fable 5 (https://claude.com/blog/a-field-guide-to-claude-fable-finding-your-unknowns).
Process
-
Read before you ask. Look at whatever is already available: the folder, the files the user mentioned, recent related work. Never ask a question you could answer yourself by reading. Questions you burned on discoverable facts are questions you cannot spend on real unknowns.
-
Interview, one question at a time. Ask 5 to 7 questions maximum, one per turn, in plain language. Prioritise questions whose answer would change the shape of the work: the audience, the decision this output feeds, what already exists, what must not change. Push past vague answers: if the user says "make it better," ask what better looks like and how you would both know it happened.
-
Cover four things by the end of the interview:
- What already exists and where it lives.
- The goal: what this output enables, and for whom.
- Which decisions the user actually cares about. Everything they do not claim is your call.
- What proof of done looks like: how they want the result verified before they see it.
-
Run a blind spot pass. Before writing the brief, ask yourself one final question and share the answer: what has this interview not covered that could change the outcome? Name the unknown unknowns you can see.
-
Write the brief back. Compile everything into one master brief with these parts: the job, the why (who it is for and what it enables), the guardrails (scope, what not to touch), and done-means (exit criteria, deliverable size, how to report back). Show it to the user.
-
On approval, execute the brief. Check in only at decisions the user claimed in step 3.
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.
- 7d ago First seen · 36 lines · 87 tokens per session scan A 8464bdd5ae14
interview-me is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 641 once invoked, about $0.0004 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 2026-09-05.
Other skills, from other repositories
project
A single starting point for setting up an AI-assisted project in Claude Cowork. It asks questions about the work, reviews available add-ons, and creates project instructions, custom agents, and connected workflows.
design-sync-upload
An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.
doc-html-slide
A renderer that turns presentation content into a single HTML slide deck that opens directly in a browser. It creates a 16:9 slide sequence with navigation, fullscreen viewing, printing to PDF, and speaker-note controls.
cs-channel-message
A channel-message writing tool for search ads, advertising, customer relationship messages, and app notifications. It uses the NCM sequence—Need, Channel, Moment, Message, and CTA—to adapt wording to where and when customers see it.
design-tokens-transformer
A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.
media-higgsfield-explainer
A Higgsfield workflow for making non-photorealistic narrated explainer videos. It pairs each narration line with a 10-second animated clip and joins the clips into one finished video.