Interview Coach is a Claude Code-based coaching system for the full job-search process, including job-description analysis, application materials, interview practice, answer evaluation, and offer negotiation. It is intended for job seekers who want tailored feedback and structured preparation based on their own experience and interview transcripts. Its catalogue entry consists of commands, a setting, and a skill that provide the coaching workflows.
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 commands/noamseg/interview-coach-skill/questionsgit clone --depth 1 https://github.com/noamseg/interview-coach-skillWrote 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/commands/noamseg/interview-coach-skill/questions)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/questions"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/questions.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 5.1 | $0.00000 | $0.00943 |
| Opus 5 | $0.00000 | $0.00472 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
questions 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
questions — Questions To Ask Workflow
Generate 5 questions with clear intent, interviewer fit, and follow-up preparation. Questions are strategic tools, not afterthoughts. Each question should serve at least one purpose:
- Information gathering: Surface something the candidate needs to know to evaluate the role
- Concern mitigation: Indirectly demonstrate a strength that addresses a known concern
- Differentiation: Show depth of thinking that makes the candidate memorable
- Rapport building: Connect with the interviewer's specific interests or background
Stage Adaptation
Adapt questions to where the candidate is in the interview loop:
- Phone screen / recruiter call: Focus on logistics, role clarity, and process. "What does success look like in the first 90 days?" Don't ask deep strategic questions — save those.
- Hiring manager round: Focus on team dynamics, priorities, and how they evaluate. "What's the biggest challenge the team is facing right now?" A powerful technique: reverse the high-signal question themes that experienced interviewers use to evaluate candidates (compiled from 150+ hiring leaders via Lenny's Podcast — see
prep.mdHigh-Signal Question Patterns). Instead of being asked "Tell me about a time things didn't go as planned," ask the hiring manager: "What's the most recent thing that didn't go as planned on the team, and how did the team handle it?" This demonstrates depth, creates conversational symmetry, and surfaces genuine information about team culture. - Final round / exec: Focus on company direction, strategic bets, and culture. "What's the most important thing this team needs to get right in the next year?"
- Peer round: Focus on collaboration, day-to-day, and honest experience. "What's something you wish you'd known before joining?"
Stage detection logic (in priority order):
- If the user specified a stage in the command (e.g.,
questions hiring manager), use that. - If
coaching_state.mdhas an active Interview Loop for a company with a known next round, use that stage. - If a
prepbrief was recently generated, infer from the format identified there. - If none of the above, ask: "What stage is this for? Phone screen, hiring manager, final round, or peer interview? The questions I generate will be very different depending on who you're talking to."
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.
- 6d ago First seen · 60 lines · 0 tokens per session scan A 5a8ec51b1c7d
questions is a command published in the GitHub repository noamseg/interview-coach-skill (2,112 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 943 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.