negotiate

negotiate is a command for Claude Code from noamseg/interview-coach-skill. It costs 0 tokens per session (6,474 once invoked), scanned A, original, MIT.

A negotiation-coaching workflow for evaluating a job offer and preparing what to say during discussions with an employer.

In plain words
What is it for?
Use it to compare salary, equity, bonus, title, level, location, and other terms, prepare negotiation scripts, and understand basic equity trade-offs. It does not provide tax, legal, or financial-planning advice.
Why use it?
It organizes the offer details, the candidate’s goals and limits, and their alternatives so they can weigh trade-offs and negotiate deliberately.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: positional $N argument.

Good fit Use it to compare salary, equity, bonus, title, level, location, and other terms, prepare negotiation scripts, and understand basic equity trade-offs. It does not provide tax, legal, or financial-planning advice.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/noamseg/interview-coach-skill/negotiate
About the project

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.

noamseg/interview-coach-skill · 2,142 stars · on GitHub

Install

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.

Clone the repo
git clone --depth 1 https://github.com/noamseg/interview-coach-skill

Made for: Claude Code.

Wrote 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.

agentmods badge for negotiate

README.md
[![agentmods](https://agentmods.dev/badge/commands/noamseg/interview-coach-skill/negotiate.svg)](https://agentmods.dev/commands/noamseg/interview-coach-skill/negotiate)
Your own site
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,474 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 018f01fa49f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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.

references/commands/negotiate.md · 273 lines

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

  1. Check coaching state. If coaching_state.md exists 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."
  2. Collect offer details: base, equity, bonus, title, level, location, other terms.
  3. Ask: "What's your ideal outcome? What's your walk-away point?"
  4. Ask: "Do you have competing offers or leverage? What's your BATNA?"
  5. Assess negotiation position and provide coaching.
  6. Log the offer to coaching_state.md Outcome Log (Result: offer) so progress and reflect can 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).

Read the full file on GitHub · 273 lines

Changes

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.

  1. 7d ago First seen · 273 lines · 0 tokens per session scan A 018f01fa49f4

Subscribe to this mod's changes

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.