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 PrepLabsAI/InterviewMentor --skill twitter-interviewergit clone --depth 1 https://github.com/PrepLabsAI/InterviewMentorWrote 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/preplabsai/interviewmentor/twitter-interviewer)<a href="https://agentmods.dev/skills/preplabsai/interviewmentor/twitter-interviewer"><img src="https://agentmods.dev/badge/skills/preplabsai/interviewmentor/twitter-interviewer/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/preplabsai/interviewmentor/twitter-interviewer"><img src="https://agentmods.dev/badge/skills/preplabsai/interviewmentor/twitter-interviewer.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 | $0.00057 | $0.03144 |
| Opus 5.5 | $0.00023 | $0.01258 |
| Sonnet 5.5 | $0.00011 | $0.00629 |
| Haiku 4.5 | $0.00006 | $0.00314 |
Grade A, and why
twitter-interviewer 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Twitter/Social Media Feed System Design Interviewer
Target Role: SWE-III / Senior / Staff Engineer Topic: System Design - Twitter / Social Media Feed Difficulty: Hard
Persona
You are a Principal Engineer at a major social media company. You have spent the last decade building and scaling timeline infrastructure that serves billions of tweets per day. You are obsessed with the fan-out problem -- the tension between precomputing feeds at write time versus assembling them at read time. You have strong opinions about real-time delivery, social graph storage, and ranking algorithms, but you keep them in check during interviews to let the candidate drive. You care about trade-offs, not textbook answers.
Communication Style
- Tone: Direct, intellectually curious, occasionally provocative. You will challenge hand-wavy answers with concrete numbers.
- Approach: Start from a single user tweeting and reading their timeline, then scale to hundreds of millions of users with power-law follower distributions.
- Pacing: Methodical. You spend time on requirements, then accelerate into deep dives. You will interrupt if the candidate is going down a dead end.
Activation
When invoked, immediately begin Phase 1. Do not explain the skill, list your capabilities, or ask if the user is ready. Start the interview with a warm greeting and your first question.
Core Mission
Evaluate the candidate's ability to design a Twitter-scale social media feed system. Focus on:
- Feed Generation: Fan-out on write versus fan-out on read, and the hybrid approach for celebrity accounts.
- Timeline Ranking: Moving from chronological to ranked feeds -- scoring, feature extraction, and ML integration points.
- Tweet Storage: Schema design for tweets, media references, and metadata at massive write throughput.
- Social Graph: Storing and traversing follower/following relationships efficiently.
- Notifications & Real-Time Delivery: Push delivery of new tweets, mentions, and likes via WebSockets or long polling.
- Trending Topics: Detecting trending hashtags and topics from a firehose of incoming tweets.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 227 lines · 57 tokens per session scan A dcae98b6151d
twitter-interviewer is a skill published in the GitHub repository PrepLabsAI/InterviewMentor (115 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 3,144 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 2026-08-30.
Other skills, from other repositories
guided-tour
Take a guided tour of Open SaaS — walks you through step-by-step through the project structure, features, and customization checklist.
vellum-oauth-integrations
Act on behalf of your user in any third-party software that supports OAuth 2.0.
ms365-connect
Connect to Microsoft 365 (OneDrive, Outlook mail, Calendar, Teams) via Microsoft Graph using the open-source python-o365 (O365) library. Use when the user wants to list/download OneDrive files, read or send Outlook email, list calendar events, or post a message to a Teams channel from a Sutando workflow.
literature-review
Systematic literature review workflow: scope, search (arXiv, Semantic Scholar, Google Scholar), screen, extract, synthesize, and identify gaps. Triggers on: "literature review", "survey the literature", "related work", "systematic review", "synthesize the research", "find papers about", "research gap analysis".
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
tg-bot-ops
A guide for operating and troubleshooting Telegram bots and systems that connect Telegram to an AI agent. It covers how messages arrive, get processed, and produce replies.