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.
git 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/thankyou)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/thankyou"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/thankyou/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.
<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/thankyou"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/thankyou.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00654 |
| Opus 5 | $0.00000 | $0.00327 |
| Sonnet 5 | $0.00000 | $0.00131 |
| Haiku 4.5 | $0.00000 | $0.00065 |
Grade A, and why
thankyou 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
thankyou — Follow-Up Workflow
Coaching State Integration
Before drafting, check coaching_state.md for data that strengthens the thank-you:
- Interview Loops: Pull interviewer names, round context, stories used, and signals observed from the most recent
debriefentry. - Interviewer Intelligence: If interviewer profiles were researched during
prep, reference shared interests or background to personalize the note. - Storybank: If
debrieflogged which stories were used and how they landed, use positive-signal stories as callback material ("I especially enjoyed discussing [topic from the story that landed well]").
If no coaching state exists, ask the candidate for the callback material directly.
Timing Guidance
Before drafting, advise on timing:
- Same day (within 2-4 hours): Standard best practice for most companies. Shows enthusiasm without being desperate.
- Next morning: Acceptable if the interview was late in the day. Can feel more thoughtful.
- Never wait more than 24 hours: After that, you've missed the window.
- If you haven't heard back (after expected timeline): Wait until 1-2 business days past the stated timeline, then send a brief check-in. Don't follow up more than twice.
Interview-Specific Callbacks
A generic "thanks for your time" is forgettable. A strong thank-you references a specific moment from the conversation:
- Pull from
analyzeormockdata if available: "I especially enjoyed our discussion about [specific topic from transcript]." - If the candidate remembers a particular exchange, weave it in: "Your question about [X] got me thinking further about [Y]."
- If the interviewer shared something personal or professional, acknowledge it: "I appreciated you sharing your perspective on [topic]."
- Keep it brief — one specific callback, not a recap of the entire interview.
Multi-Interviewer Handling
If the candidate met multiple interviewers in the same round, generate separate drafts for each person:
- Each note should reference something specific to that interviewer's questions or conversation.
- Vary the tone slightly — don't send identical notes (interviewers compare).
- The core message can be similar, but the callback and angle should differ.
- Ask the candidate: "Who did you meet with? What stood out from each conversation?"
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.
- 9d ago First seen · 63 lines · 0 tokens per session scan A eb9c590e08d7
thankyou is a command published in the GitHub repository noamseg/interview-coach-skill (2,160 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 654 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.