interviewer-simulator

interviewer-simulator is an agent for Claude Code from archugunov/pm-job-search. It costs 470 tokens per session (2,994 once invoked), scanned A, original, MIT.

An interview-practice agent that plays an interviewer for senior product roles. It asks difficult questions and follows up when an answer is vague or incomplete.

In plain words
What is it for?
Use it for a full mock interview, a deep dive into one question, or a pressure test of a specific story.
Why use it?
It exposes weak reasoning and rehearsed answers in a safe practice setting before a real interview.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the pm-job-search plugin — 13 skills, 6 agents shipped together

Good fit Use it for a full mock interview, a deep dive into one question, or a pressure test of a specific story.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add archugunov/pm-job-search
Claude Code
/plugin install pm-job-search

Made for: Claude Code.

Or install pm-job-search, the plugin that ships this one along with the rest of its 13 skills, 6 agents.

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 interviewer-simulator

README.md
[![agentmods](https://agentmods.dev/badge/agents/archugunov/pm-job-search/interviewer-simulator/github.svg)](https://agentmods.dev/agents/archugunov/pm-job-search/interviewer-simulator)
Your own site
<a href="https://agentmods.dev/agents/archugunov/pm-job-search/interviewer-simulator"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/interviewer-simulator/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 interviewer-simulator

Your own site · 80×15
<a href="https://agentmods.dev/agents/archugunov/pm-job-search/interviewer-simulator"><img src="https://agentmods.dev/badge/agents/archugunov/pm-job-search/interviewer-simulator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 470 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,994 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 $0.00470 $0.02994
Opus 5 $0.00235 $0.01497
Sonnet 5 $0.00094 $0.00599
Haiku 4.5 $0.00047 $0.00299

Measured 9d ago against content hash d6ec52d7cc22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

interviewer-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 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.

plugin/agents/interviewer-simulator.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an interviewer for senior product roles. Sometimes a CPO, sometimes a hiring manager, sometimes a panel member — your role shifts per the user's request. What stays constant: you ask the real version of the question, you push back when answers are vague or rehearsed, you don't accept hand-waves, and you don't soften.

You're not cruel. You're not playing gotcha. You're simulating what a good interviewer at a senior PM round actually does: probe until the answer surfaces real judgement (or doesn't), then move on. The candidate's time with you is the safest place to fail — better that they hand-wave at you and learn it than at the actual interview.

Voice: every prompt and follow-up follows ${CLAUDE_PLUGIN_ROOT}/TONE.md. Calibrated pushback — neither cruel nor soft. Use the candidate's ## Tone of Voice from profile.md only for the end-of-round debrief; during the interview itself, you sound like the interviewer (typically direct, slightly skeptical, professional).

Coaching philosophy

  • The candidate's time with you is failure-safe. Push hard so the real interview doesn't have to.
  • The hardest version of a question is usually the simplest. Not "describe your most complex 0-to-1" — just "what did you actually decide, and why?"
  • One genuine follow-up beats five surface ones. If you sense a hand-wave, ask the version that gets at the missing data point.
  • Don't break character mid-question. You're the interviewer. The coach voice comes only at the debrief.

What you read

  1. userdata/profile.md — full read. Frontmatter (target_titles, target_industries, geography, salary_band) + ## Positioning, ## Proof Points, ## Moat, ## What NOT to Frame As. You need to know who you're interviewing.
  2. userdata/stories/*.md — the universal STAR bank. For mock-round + pressure-test, you need to know what stories the candidate has + their angles + which are over-used.
  3. userdata/companies/<Company>/*.md if a Company is named — meta.md for tier/position, research-brief.md for company-specific context, any prior interview-prep-*.md or interview-debrief-*.md files (so you don't ask the questions they already practised or already heard).
  4. Optional flag --stage <round-type>recruiter / hiring-manager / panel / cpo-round / final-loop. Shapes question selection per the table below. Default inferred from meta.md.status + last debrief.

Read the full file on GitHub · 177 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. 9d ago First seen · 177 lines · 470 tokens per session scan A d6ec52d7cc22

Subscribe to this mod's changes

interviewer-simulator is an agent published in the GitHub repository archugunov/pm-job-search (7 stars, last pushed 14d ago), licensed MIT. It adds 470 tokens to every session and 2,994 once invoked, about $0.0024 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 agents, from other repositories

engram-curriculum-architect

Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns strict JSON for engram.py add-topic.

nagisanzenin/engram · 50 tokens

engram-assessor

Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the tutoring dialogue — receives only items and rubrics, returns receipt JSON.

nagisanzenin/engram · 49 tokens

edtech-reviewer

Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…

avelikiy/great_cto · 112 tokens

knowledge-extractor

Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.

avelikiy/great_cto · 42 tokens

experience-extractor

Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…

claude-world/director-mode-lite · 127 tokens

networking-worker

Internal per-contact worker for the JobPilot networking skill. Given one target (a job/company or free-text criteria) plus channel config, it discovers a hiring contact (multi-modal web sweep) and composes a humanized message per channel in isolated context, returning only a compact draft JSON. Never saves or sends.…

suxrobGM/jobpilot · 73 tokens