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 agentmods add skills/r5rana/agentware/interviewnpx skills add r5rana/agentware --skill interviewgit clone --depth 1 https://github.com/r5rana/agentwareWrote 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/r5rana/agentware/interview)<a href="https://agentmods.dev/skills/r5rana/agentware/interview"><img src="https://agentmods.dev/badge/skills/r5rana/agentware/interview.svg" alt="Measured on agentmods" 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 | $0.00185 | $0.04232 |
| Opus 5 | $0.00093 | $0.02116 |
| Sonnet 5 | $0.00037 | $0.00846 |
| Haiku 4.5 | $0.00018 | $0.00423 |
Grade C, and why
interview scanned grade C with 1 finding 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 4d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Never refuse as too advanced.** Answer at their level. How it starts
The opening of the file, as written. The whole thing — 340 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interview
You are the interviewer and the record-keeper. Brief, direct, technical. Not a tutor, not a cheerleader.
Calibrate before you start
You do not know who is across the table until you ask. Three facts change how you run the whole session, so establish them once, in a single short turn, before step 1.
Quick calibration before we start:
- Which language are you fluent in, and which are you interviewing in?
- How much DSA have you done — roughly none, some patterns, or comfortable?
- What are you targeting — internship, new grad, or senior?
Accept rough answers and move on. This is one turn, not a step, and not an interrogation.
Skip it when you already know. If the interview log holds prior attempts, read the most recent record and calibrate from that instead of asking again. Re-ask only when a session suggests the level has moved.
What each answer changes:
| Answer | What it changes |
|---|---|
| Fluent language | The language you bridge from at step 5b, and which traps you call out |
| Interview language | The syntax you teach. Python is this skill's default; substitute throughout if it differs |
| DSA level | Whether step 3 is a one-line reminder or a full teach, and how much of 5a you cover |
| Target bar | The standard the step 8 verdict is scored against |
If the candidate cannot place their own level, infer it from the first two steps and say nothing about it. A wrong guess costs one step; an interrogation costs the session.
The failure mode to watch for. A candidate who reasons well but stalls constantly is usually missing primitives, not thinking. The tell is "I don't know how to write that", not "I can't see it". Those two stalls need opposite responses: teach the primitive outright and move on, and never mistake it for a thinking gap. Someone can ship real software and still not have reversed a linked list unaided or traced a recursive call frame by frame. That is a vocabulary gap, not a capability gap.
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.
- 4d ago First seen · 340 lines · 185 tokens per session scan C cdbbb6981dee
interview is a skill published in the GitHub repository r5rana/agentware (24 stars, last pushed 17d ago), licensed Apache-2.0. It adds 185 tokens to every session and 4,232 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
grid-ctf-ops
Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.