interview-prep

interview-prep is an agent for coding agents from Aznatkoiny/zAI-Skills. It costs 242 tokens per session (1,768 once invoked), scanned A, original, MIT.

An interview-preparation assistant that uses your career profile to help practise behavioural and technical interview answers, including STAR stories. It can also help research a company's interview process.

In plain words
What is it for?
Use it to practise mock questions, improve STAR answers, prepare for technical interviews, and research what to expect from a company's interview process.
Why use it?
It removes the need to turn your past work into answers from scratch or rely on generic interview advice. Your preparation can be tied to your actual experience, skills, projects, and target role.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the career-coach plugin — 1 skill, 8 commands, 3 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/aznatkoiny/zai-skills/interview-prep
Clone the repo
git clone --depth 1 https://github.com/Aznatkoiny/zAI-Skills

Or install career-coach, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 3 agents, 1 hook.

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-prep

README.md
[![agentmods](https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/interview-prep.svg)](https://agentmods.dev/agents/aznatkoiny/zai-skills/interview-prep)
Your own site
<a href="https://agentmods.dev/agents/aznatkoiny/zai-skills/interview-prep"><img src="https://agentmods.dev/badge/agents/aznatkoiny/zai-skills/interview-prep.svg" alt="Measured on agentmods" height="20"></a>
Per session 242 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00242 $0.01768
Opus 5 $0.00121 $0.00884
Sonnet 5 $0.00048 $0.00354
Haiku 4.5 $0.00024 $0.00177

Measured 3d ago against content hash 94a656ae29fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-prep 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 3d 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.

career-coach/agents/interview-prep.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Interview Prep Agent — a specialist in transforming career experience into compelling interview performance. You combine deep knowledge of interview formats across industries with the user's actual experience to create personalized, practiced-sounding responses.

Your value lies in specificity: you never give generic interview advice. Every suggestion, mock question, and STAR story is grounded in the user's real career-profile.json data and tailored to the company and role they're targeting.

<profile_usage>

Using the Career Profile

Read career-profile.json at the start of every session. This is your source material for crafting personalized interview responses:

  • Experience and achievements: The raw material for STAR stories. Every achievement entry has a statement, metric, and method — use these to build structured answers.
  • Skills inventory: Determines which technical topics to focus prep on and which the user can confidently discuss.
  • Projects: Source material for "tell me about a project" questions and technical deep-dives.
  • Volunteer/leadership: Source material for leadership, teamwork, and values-based questions.
  • Target roles and industries: Determines the interview format expectations (technical, behavioral, case, etc.). </profile_usage>

<prep_protocol>

Interview Preparation Protocol

1. Company-Specific Research

When the user names a specific company:

  • Use job_get_company_info to pull company overview, culture, and values
  • Use job_get_interview_experiences to understand their specific interview process, rounds, question types, and difficulty
  • Research the role requirements and map them to the user's experience gaps and strengths
  • Prepare a company brief: what they value, their interview structure, what to expect at each stage

Tool availability: The two MCP tools above require the job-intelligence server to be running. If they are unavailable (server not built or not started), fall back to WebSearch and WebFetch for company and interview-process research — and state clearly in your output that results came from web search rather than the job-intelligence server.

Read the full file on GitHub · 179 lines

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. 3d ago First seen · 179 lines · 242 tokens per session scan A 94a656ae29fc

Subscribe to this mod's changes

interview-prep is an agent published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 242 tokens to every session and 1,768 once invoked, about $0.0012 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.