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/debriefgit 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/debrief)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/debrief"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/debrief.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 | $0.01923 |
| Opus 5 | $0.00000 | $0.00962 |
| Sonnet 5 | $0.00000 | $0.00385 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
debrief 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
debrief — Post-Interview Rapid Capture Workflow
Captures what happened in a real interview while it's still fresh. This is the bridge between the real interview and analyze — and for candidates without transcripts, it may be the only data source.
When to Use
- Immediately after a real interview (same day, ideally within 1-2 hours)
- When the candidate doesn't have a transcript
- When they do have a transcript but want to capture subjective impressions before analysis
- When they need emotional processing before diving into scoring
Sequence
-
Emotional check first. Before anything tactical, ask: "How are you feeling about it? One word." This serves two purposes: (a) it surfaces emotional state that affects memory quality, and (b) it shows the coach cares about the person, not just the performance. Don't skip this.
-
Rapid question capture. "What questions did they ask? Don't worry about exact wording — just get them down." Capture as many as they can remember. Prompt with format cues: "Was there a behavioral question? A 'tell me about a time' question? Anything unexpected?"
-
Per-question self-assessment. For each question they remember: "How did you feel about your answer? Strong, okay, or rough?" Don't score yet — capture their in-the-moment read.
-
Signal reading. "Did you notice any signals from the interviewer? Follow-up questions that showed interest? Moments where they seemed to lose interest or redirect? Any body language that stood out?" Capture these — they're high-value data even without a transcript.
Signal Interpretation Guide — Help the candidate read the signals they noticed:
Signal Likely Meaning Confidence Extended follow-ups on one topic Genuine interest or evaluating depth — positive either way HIGH Interviewer moved on quickly after your answer Your answer either fully satisfied them or didn't land — look at their energy after moving on MEDIUM "That's interesting" + follow-up Usually positive — they want more HIGH Interviewer checked the time or clock Running behind schedule, not necessarily boredom — but if repeated, you may be going long MEDIUM "Let me push back on that" Testing conviction, not disagreeing — this is often a positive signal HIGH Interviewer started selling the role/company to you Strong buy signal — they want you interested HIGH Short, closed-ended follow-ups They may have already formed their assessment — neutral to negative MEDIUM "We'll be in touch" with no specifics Standard — don't read into it either way LOW
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 · 122 lines · 0 tokens per session scan A eaf29a758c76
debrief 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 1,923 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
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.