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/reflectgit 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/reflect)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/reflect"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/reflect.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 | $0.01331 |
| Opus 5 | $0.00000 | $0.00665 |
| Sonnet 5 | $0.00000 | $0.00266 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
reflect 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
reflect — Post-Search Retrospective Workflow
Closes the loop on a coaching engagement. Run when the candidate has accepted an offer, decided to pause their search, or wants to take stock after a sustained effort.
When to Trigger
Suggest reflect when:
- The candidate reports accepting an offer
- The candidate says they're pausing or stopping their search
- 8+ sessions have been completed with no recent activity
- The candidate asks "what did I learn?" or "how did I do overall?"
Sequence
- Acknowledge the milestone. Whether it's an offer, a pause, or a pivot, name it: "You've been at this for [duration]. Let's look at the full arc." Don't skip this — the candidate deserves recognition for the work they put in.
- Pull the full data. Review all of
coaching_state.md: score history, outcome log, storybank evolution, drill progression, Active Coaching Strategy. - Narrate the journey. This is not a progress report — it's a story about growth:
- Where did they start? (kickoff baseline)
- What were the biggest breakthroughs? (inflection points from score history)
- What was hardest to improve? (persistent patterns)
- What's genuinely different about how they interview now vs. when they started?
- Initial vs. final self-assessment comparison: Pull the candidate's initial concerns and self-assessment from kickoff (biggest concern, interview readiness assessment) and compare to their most recent
progresscalibration data. Show the delta: "You started thinking your biggest weakness was [X]. Turns out it was [Y]. Your initial self-assessment was [over/under/accurate] — and your calibration improved to [current accuracy]." This bookend comparison makes growth tangible.
- Extract transferable lessons. What did they learn that applies beyond this job search?
- Communication skills that transfer to the job itself — the interview coaching skills map directly to Ethan Evans' Magic Loop framework, step 2: "Tell the right people about your work" (via Lenny's Newsletter). The candidate has practiced structured communication, positioning, and storytelling under pressure — these are the exact skills that drive visibility and career growth in the new role.
- Self-awareness insights (self-assessment calibration patterns)
- Storytelling ability that helps in presentations, stakeholder management, etc.
- Wes Kao's concept of "minimum viable opinions" (MOPs, via Lenny's Podcast) applies to the transition into a new role: form and articulate provisional opinions early, even before having full context. The structured thinking skills developed through interview coaching — framing, evidence-based reasoning, acknowledging uncertainty — are exactly what MOPs require.
- If they got an offer: What made the difference? Which dimensions were strongest in the interviews that advanced? Which stories landed? What changed between early rejections and later advances?
- If they didn't get an offer (or are pausing): Honest diagnosis without blame. What are the remaining gaps? Are they coachable with more practice, or do they suggest a targeting adjustment? What should they focus on if/when they resume?
- Archive and close.
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 · 104 lines · 0 tokens per session scan A f6bb60563c37
reflect is a command published in the GitHub repository noamseg/interview-coach-skill (2,092 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,331 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
git
Git operations with intelligent commit messages and workflow optimization.
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.