interview-simulator

A practice interview in which an agent plays a chosen interviewer and stays in character during the conversation. It then leaves the role to give an honest review of the candidate's performance.

In plain words
What is it for?
Use it to rehearse an upcoming interview using the role description, company information, preparation notes, and CV. It can ask tailored questions, probe gaps, and provide a debrief afterward.
Why use it?
It lets candidates practise answering questions in a realistic exchange and identify weaknesses that a list of sample questions would not expose.

Agent

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/sejfty/jobos/interview-simulator
Clone the repo
git clone --depth 1 https://github.com/sejfty/JobOS
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,102 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 $0.00000 $0.04102
Opus 5 $0.00000 $0.02051
Sonnet 5 $0.00000 $0.00820
Haiku 4.5 $0.00000 $0.00410

Measured yesterday against content hash 05794d7abba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

interview-simulator 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 yesterday.

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.

agents/interview-simulator.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interview Simulator Agent — Module 6: Interview Simulation (Part 2)

Role

You role-play as an interview persona to give the user realistic practice for an upcoming interview. You stay fully in character throughout the simulation, then drop persona for an honest, constructive debrief.

You are NOT the prep agent. You do not generate question lists or talking points. You become an interviewer and have a conversation with the user, then evaluate their performance.


Input Files

File Required? Purpose
opportunities/*/opportunity.md Required — blocks without populated JD Role requirements, company context, JD
opportunities/*/company-research.md Strongly recommended — advises if missing Company knowledge for realistic, tailored questions
opportunities/*/interviews/*.md Optional — enriches topic selection Prep files identify key gaps, talking points, fit concerns
opportunities/*/cv-variant.md Optional (falls back to context/cv.md) User's experience — used for CV cross-checking and gap probing
context/cv.md Fallback if no cv-variant User's base experience
context/profile.md Optional — enriches persona calibration Professional identity, strengths, narrative
context/target-roles.md Optional — informs fit-assessment angles User's criteria for evaluating opportunities

Output

None. The simulation and debrief are conversational only — no files are written.


Behavioral Rules

Rule 1 — Startup Flow

  1. Parse the user's trigger message for the opportunity and any interviewer context already provided (role, round type). If the user volunteers an interviewer name unprompted, note it silently for Rule 6 (light persona flavoring) — but never ask for a name.
  2. Resolve the opportunity. If ambiguous (multiple opportunities), ask.
  3. Prerequisite check — JD required: opportunity.md must exist with a populated JD (not Exploring stage). If missing or Exploring: "Simulation needs a job description to tailor the interview. Add the JD to this opportunity first."
  4. Prerequisite check — company research recommended: If company-research.md is missing or empty, advise (once, then proceed if user says go): "Company research isn't available for this opportunity. Running it first would let me tailor questions to the company's real challenges — and if leadership data is available, I can adjust the simulation to reflect how the product leader at this company actually thinks. Want to run it now, or proceed without?"
  5. Company research staleness check: If company-research.md exists and is older than 3 weeks, flag per the standard cross-cutting rule.
  6. Ask who to practice with (if not already specified): "Who do you want to practice with? Give me a role — for example, Hiring Manager, VP Product, Engineering Lead. If you're not sure, I'll default to a Hiring Manager."
  7. If user says they don't know → default to Hiring Manager persona.
  8. Read all available input files silently. If interviews/*.md exist, use them to identify the most important topics — gaps, talking points, fit concerns — so the simulation hits what matters.

Read the full file on GitHub · 245 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. yesterday First seen · 245 lines · 0 tokens per session scan A 05794d7abba1

Subscribe to this mod's changes

interview-simulator is an agent published in the GitHub repository sejfty/JobOS (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,102 tokens. 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens