interview-mode

interview-mode is a skill for Claude Code, Codex from yugash007/edu-agent-skills. It costs 26 tokens per session (717 once invoked), scanned A, original, MIT.

A simulated technical interview in which the agent acts as the interviewer and the learner explains their thinking under agreed time and hint conditions. Teaching and feedback happen after the simulation.

In plain words
What is it for?
Use it for coding, system-design, or combined technical interview practice. It helps set the interview format, ask questions, observe explanations, and route weak areas to later practice.
Why use it?
It reveals gaps in both technical reasoning and communication before a real interview. The practice can also help learners get used to answering under pressure.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for coding, system-design, or combined technical interview practice. It helps set the interview format, ask questions, observe explanations, and route weak areas to later practice.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yugash007/edu-agent-skills/interview-mode
Install

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.

Any agent
npx skills add yugash007/edu-agent-skills --skill interview-mode
Clone the repo
git clone --depth 1 https://github.com/yugash007/edu-agent-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for interview-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/interview-mode/github.svg)](https://agentmods.dev/skills/yugash007/edu-agent-skills/interview-mode)
Your own site
<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/interview-mode"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/interview-mode/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.

agentmods 80×15 button for interview-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/yugash007/edu-agent-skills/interview-mode"><img src="https://agentmods.dev/badge/skills/yugash007/edu-agent-skills/interview-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 717 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.00717
Opus 5 $0.00013 $0.00358
Sonnet 5 $0.00005 $0.00143
Haiku 4.5 $0.00003 $0.00072

Measured 9d ago against content hash 7d30cc7ee1d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

interview-mode 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 9d 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.

skills/assessment/interview-mode/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Simulate realistic technical interview conditions. Act as an interviewer (not teacher) during simulation. The debrief phase switches back to teaching mode.

Activation

  • Learner asks for interview practice or mock interview. Upcoming technical interview. Building communication fluency. check-understanding shows learner knows material but struggles to articulate.
  • Skip if: learner lacks foundational understanding → teach-concept first. Session is exploratory/onboarding.
  • Routing: don't mix interview-mode with teaching mid-session. After simulation, hand off to misconception-detector or check-understanding for remediation. If learner panics: pause and switch to socratic-mode.

Inputs

  • Interview type (coding/system design/behavioral+technical), target topic, learner level and confidence, time constraint preference (relaxed/timed/strict), known weak areas to probe.

Workflow

  1. Setup — Confirm type, topic, time pressure. State framing: "I'll act as the interviewer. Speak as you would in a real interview." Set scope: duration, question count, hint availability.
  2. Warm-Up — One confidence-building question below target difficulty. Evaluate communication style alongside correctness.
  3. Core Question(s) — 1–2 questions at target difficulty. Coding: problem statement + constraints, ask for approach before code. System design: realistic scenario, ask for requirements clarification first. Don't interrupt mid-reasoning — note gaps for debrief.
  4. Probe — 2–3 follow-ups per core answer: edge cases not mentioned, avoided tradeoffs, scalability, failure modes, alternatives.
  5. Close Simulation — Signal end. No evaluative feedback yet — maintain interviewer framing until this point.
  6. Debrief — Score on 4 dimensions (1–5): Correctness, Communication, Tradeoff Awareness, Edge Case Coverage. For each below 4: specific gap + corrective action.
  7. Remediation — Surface top 1–2 weaknesses. Recommend follow-up skill (teach-concept, socratic-mode, or challenge-generator).

Read the full file on GitHub · 56 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 56 lines · 26 tokens per session scan A 7d30cc7ee1d2

Subscribe to this mod's changes

interview-mode is a skill published in the GitHub repository yugash007/edu-agent-skills (7 stars, last pushed 3mo ago), licensed MIT. It adds 26 tokens to every session and 717 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

learning-coach

A Chinese-language personal coaching guide for learning programming, AI agents, writing, languages, exams, research, or career skills through real projects and tasks. It tracks progress and teaches one useful action at a time.

chrichuang218/ai-learning-coach · 179 tokens

understand-explain

Use when you need a deep-dive explanation of a specific file, function, or module in the codebase.

Egonex-AI/Understand-Anything · 27 tokens

baoyu-comic

A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.

JimLiu/baoyu-skills · 61 tokens

ctf-misc

Provides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Use for encoding puzzles, pyjails, bash jails, RF/SDR, DNS oddities, unicode tricks, esoteric languages, QR or audio puzzles, constraint solving, game theory, unusual sandbox escapes, and hybrid logic puzzles.…

ljagiello/ctf-skills · 122 tokens

slide-excellence

Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…

pedrohcgs/claude-code-my-workflow · 94 tokens

respond-to-eval

Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the…

pedrohcgs/claude-code-my-workflow · 111 tokens