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/hypegit 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/hype)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/hype"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/hype.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 | $0.00000 | $0.02854 |
| Opus 5 | $0.00000 | $0.01427 |
| Sonnet 5 | $0.00000 | $0.00571 |
| Haiku 4.5 | $0.00000 | $0.00285 |
Grade A, and why
hype 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 5d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hype — Pre-Interview Boost Workflow
Data-Driven Hype
The hype reel should be built from real coaching data, not generic encouragement:
- Pull from practice high points: Reference the candidate's best practice moments — "In your last practice session, you nailed the prioritization question with a 4 on Structure. That's the level you're bringing today."
- Reference strongest stories: Name the 2-3 stories that scored highest in the storybank and are mapped to this interview.
- Use real score trajectory: If scores have been improving, name it — "Your Structure scores went from 2s to consistent 4s over the last three sessions. That's not luck."
- If no coaching data exists yet (first session), build from resume strengths and kickoff profile. Be explicit about this: "I don't have practice scores or storybank data to draw from yet — this hype reel is built from your resume and what you've told me. It'll be more powerful once we've done some practice rounds together."
Anxiety-Profile Personalization
Candidates experience pre-interview anxiety differently. During kickoff (or the first time hype is run), identify the candidate's anxiety profile from their stated concern and interview history:
| Profile | Signals | Hype Adjustment |
|---|---|---|
| Confident but underprepared | "I'm fine with interviews, just haven't prepped" | Skip emotional boost — focus on tactical 3x3 and cheat sheet. Be direct about gaps. |
| Anxious about specific failure | "I always freeze on behavioral questions" or "I can't think of stories" | Address the specific fear head-on with evidence. "You have 8 stories in your storybank, 5 rated 4+. You've practiced retrieving them under pressure. You're not going to freeze." |
| Generalized anxiety | "I'm just really nervous" or "I always feel like I'll mess up" | Lead with the physiological warmup (breathing, physical reset). Stanford communication expert Matt Abrahams recommends reframing anxiety as excitement (via Lenny's Podcast): "The physical sensations of anxiety and excitement are nearly identical — racing heart, heightened alertness. Instead of trying to calm down, relabel: 'I'm excited about this conversation.'" Provide the reframe early: "This is a conversation, not a test." Abrahams' core principle: "Strive for connection over perfection by daring to be dull. Just answer the question." When candidates stop optimizing for brilliance and optimize for genuine engagement, the anxiety drops and performance improves. Keep the hype short and grounded — too much intensity can amplify anxiety rather than reduce it. |
| Post-rejection anxiety | Recent rejection in Outcome Log, or candidate mentions a bad experience | Acknowledge it directly: "Your last interview at [Company] didn't go the way you wanted. That's done. This is a different company, different interviewers, fresh start." Reference what changed since then (new practice scores, improved stories). Executive coach Joe Hudson (via Lenny's Podcast) warns: "Whatever emotion that you're trying to avoid, you are inviting into your life in exactly the way that you're trying to avoid it." Trying not to be nervous about repeating a failure makes the anxiety worse. Instead, frame each interview as an experiment — the experimental mindset means "you can never really fail, you're just learning about yourself." |
| Impostor syndrome | "I don't think I'm qualified" or fit verdict was Investable Stretch | Ground in evidence: specific resume achievements, practice scores, storybank strengths. "The data says you belong in this interview. Let's look at why you were invited." Executive coach Katherine Hosie reframes it (via Lenny's Newsletter): "Impostor syndrome is normal and is generally a sign that you're enjoying some degree of success in your life. If you were pumping gas, you wouldn't be experiencing impostor syndrome." Then run a responsibility audit — when negative self-talk spikes, ask: "Where am I actually not taking responsibility right now?" Often impostor syndrome lifts when the candidate addresses the specific thing they're avoiding (doing prep work, practicing, asking for help). Also check sleep — as Hosie notes, sleep deprivation creates emotional fragility that candidates misattribute to genuine inadequacy. |
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.
- 5d ago First seen · 130 lines · 0 tokens per session scan A c109058dcd40
hype 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 2,854 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
lrn
Execute the /vibeguard:learn command. $ARGUMENTS.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
annex-a-deep-dive
Deep dive analysis of ISO 27001 Annex A control domains with implementation guidance.
start-10-1
Command "start-10-1" from minicoohei/ai-agent-camp, covering 🎓 lesson 10-1: clasp基本・gasプロジェクト管理, 📍 このセッションでやること, 🎯 準備チェック, 🚀 step 1: claspのインストールと apps script api の確認 and 🚀 step 2: google認証.
start-13-4.en
Welcome to Lesson 13-4: Landing Page Implementation!