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/salary)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/salary"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/salary.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 | $0.05638 |
| Opus 5 | $0.00000 | $0.02819 |
| Sonnet 5 | $0.00000 | $0.01128 |
| Haiku 4.5 | $0.00000 | $0.00564 |
Grade A, and why
salary 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 7d 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 — 332 lines — stays where its author put it; the contents beside it link to each section on GitHub.
salary — Early/Mid-Process Comp Coaching
How Comp Conversations Actually Work (Reference Knowledge)
The Anchoring Effect: The first number mentioned in a compensation conversation becomes the anchor. If a candidate says "$120K" in a recruiter screen, the final offer will orbit $120K — regardless of market rate. This makes the recruiter screen the highest-leverage comp moment. By the time negotiate fires (post-offer), the anchor is set. salary coaches the moment that sets the anchor.
When Comp Comes Up (the comp conversation timeline):
- Application form: "Expected salary" field. First anchor risk.
- Recruiter screen: "What are your salary expectations?" or "What's your current compensation?" Highest-stakes comp moment.
- Mid-process: Hiring manager mentions range informally, or recruiter checks comp alignment.
- Pre-offer: Recruiter discusses comp structure, tests whether candidate will accept.
- Formal offer →
negotiatecommand handles this stage.
salary covers stages 1-4. negotiate covers stage 5. The handoff is explicit.
The Deflection vs. Disclosure Tradeoff:
- Deflecting ("I'd like to learn more about the role first") works best early but becomes less tenable as the process progresses.
- Over-deflecting can signal difficulty, evasiveness, or game-playing.
- Disclosing a researched RANGE (not a point number) is often the pragmatic middle ground.
- Key principle: let the company share their range first when possible. The party that names a number first is at a disadvantage. See Dragova's specific deflection scripts in Step 4 below.
- Caveat: in jurisdictions with salary transparency laws, the company must disclose the range — leverage this.
- Mine for intel during interviews: Dragova advises treating every conversation with the company as an intelligence-gathering opportunity. Strategic questions like "What's the biggest priority for the team right now?", "Why is this role open?", and "What's the biggest challenge for someone stepping into this role?" provide negotiation ammunition later — and make the candidate appear engaged rather than evasive. What recruiters say when pushing for a number: "If you give me your number, I will make it happen for you." What they mean: "I'll get you something lower, but kinda close to what you asked for." Stand firm.
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.
- 7d ago First seen · 332 lines · 0 tokens per session scan A 0cb76653f7a9
salary is a command published in the GitHub repository noamseg/interview-coach-skill (2,124 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,638 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.
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.