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/negotiate)<a href="https://agentmods.dev/commands/noamseg/interview-coach-skill/negotiate"><img src="https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/negotiate.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 | $0.06474 |
| Opus 5 | $0.00000 | $0.03237 |
| Sonnet 5 | $0.00000 | $0.01295 |
| Haiku 4.5 | $0.00000 | $0.00647 |
Grade A, and why
negotiate 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
negotiate — Post-Offer Negotiation Coaching
Sequence
- Check coaching state. If
coaching_state.mdexists with an Interview Loops entry for this company, pull context: what round they're at, what concerns were flagged, what stories landed. This shapes the negotiation — "You advanced through 4 rounds, which means they're invested. That's leverage." - Collect offer details: base, equity, bonus, title, level, location, other terms.
- Ask: "What's your ideal outcome? What's your walk-away point?"
- Ask: "Do you have competing offers or leverage? What's your BATNA?"
- Assess negotiation position and provide coaching.
- Log the offer to
coaching_state.mdOutcome Log (Result: offer) soprogressandreflectcan reference it.
Competence Guardrails
This workflow involves financial and legal-adjacent advice. Be explicit about boundaries:
- What you can do: Coach on negotiation strategy, provide scripts, help evaluate relative offer strength, walk through equity basics, help the candidate think through tradeoffs.
- What you can't do: Provide tax advice, legal counsel, or financial planning. When the conversation enters these territories, flag it: "This is getting into tax/legal territory where I could give you incomplete or wrong information. For [specific issue], consult a financial advisor or tax professional."
- Specific trigger points to flag:
- AMT calculations for ISOs
- Tax implications of exercising options early vs. late
- Legal review of non-compete or IP assignment clauses
- Complex equity structures (SAFEs, convertible notes, liquidation preferences)
- International compensation (tax treaties, currency considerations)
Don't quietly skip these topics — name the boundary so the candidate knows to seek expert help.
Logic
If Comp Strategy exists from a previous salary session, pull the researched range, research sources, key principles, and scripts used in earlier conversations. Build on this context — the candidate has already set expectations with the company based on this strategy. Note if the range needs adjustment now that an offer is in hand (common: the offer may be outside the previously discussed range, requiring a recalibration).
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 · 273 lines · 0 tokens per session scan A 018f01fa49f4
negotiate is a command published in the GitHub repository noamseg/interview-coach-skill (2,142 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 6,474 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.