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/applygit 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/apply)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/apply"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/apply.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 | $0.01552 |
| Opus 5 | $0.00000 | $0.00776 |
| Sonnet 5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade C, and why
apply scanned grade C with 1 finding 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- Don't refuse to proceed — draft what's supportable and mark the flagged question clearly. How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
apply — Job Application Question Drafting
Inputs
- Required: Company name + list of application questions
- Optional: Word or character limits per question
- Optional: JD (used for "why us" tailoring and domain matching)
- Optional: Resume text (used as fallback for tools/experience questions not covered by storybank)
Sequence
Step 1: Parse and classify questions
For each question, assign one type:
- Behavioral: "Tell me about a time...", "Describe a situation where..."
- Process/method: "How do you [prioritize / use data / manage stakeholders]..."
- Tools/experience: "Do you have experience with [tool/domain]..."
- Why us: "Why this company / role / industry..."
- Other: Hypotheticals, case-style, or open-ended
State the classification before drafting each answer.
Step 2: Check for prior answers
Before drafting, scan job-search/ for existing application files from previous companies. For each question, check whether a semantically similar question was answered before. If yes:
- Surface the prior answer
- Ask: "I answered a similar question for [Company] — want me to adapt that, or draft fresh for [New Company]?"
This builds a reusable answer library across applications over time.
Step 3: Gap check before drafting
For each question, verify that the storybank (in coaching_state.md) or the provided resume contains evidence to support an answer.
If evidence is found: proceed to Step 4.
If evidence is not found (e.g., a tool never used, a domain never worked in, an experience not in the storybank or resume):
- Do not invent or imply the experience.
- Flag it explicitly: "I don't see evidence in your storybank or resume for [X]. Can you tell me about a time you [Y]? Or should we note this gap and move on?"
- Don't refuse to proceed — draft what's supportable and mark the flagged question clearly.
Step 4: Story selection (behavioral and process/method questions only)
For each behavioral or process/method question, do not auto-select a story. Instead:
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 · 150 lines · 0 tokens per session scan C 49b21cb7bab5
apply 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 1,552 tokens. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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.