A deal-analysis workflow for examining an offer and preparing a counter-proposal. It applies negotiation concepts such as alternatives, leverage, and the range where both sides might agree.

Use it to review compensation, real-estate, vendor, or resource-allocation offers and draft a counter-proposal.

It organizes the terms, gaps, risks, and missing information before you decide whether or how to respond.

negotiation — Skill for Claude Code by rjmurillo

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.

Any agent

npx skills add rjmurillo/ai-agents --skill negotiation

Clone the repo

git clone --depth 1 https://github.com/rjmurillo/ai-agents

Made for: Claude Code.

Or install project-toolkit, the plugin that ships this one along with the rest of its 113 skills, 26 commands, 33 agents, 4 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/rjmurillo/ai-agents/negotiation/github.svg)](https://agentmods.dev/skills/rjmurillo/ai-agents/negotiation)

Your own site

<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/negotiation"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/negotiation/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/negotiation"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/negotiation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,254 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00078	$0.01254
Opus 5	$0.00039	$0.00627
Sonnet 5	$0.00016	$0.00251
Haiku 4.5	$0.00008	$0.00125

Measured 6d ago against content hash 9753ad450c2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

negotiation 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 6d 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.

.claude/skills/negotiation/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Negotiation Skill

Codifies deal intelligence behavior. Use when reviewing any offer or designing how an agentic system should analyze and counter-propose. The full crystallized skill set lives in references/skills.md.

Triggers

Phrase	Context
`review this offer`	Real estate, compensation, vendor, resource allocation
`what's the value gap`	Quantification request
`draft a counter`	Counter-proposal drafting
`should I walk`	Walkaway analysis
`anchor first or wait`	Information-asymmetry decision

Skip when:

The change is descriptive ("explain how anchoring works") rather than applied. Use a knowledge response, not the skill.
The artifact is not an offer or counter (e.g., a status update).

Process

Apply the RADAR protocol in order. Skipping a step is the most common failure mode and the rule against it is load-bearing.

Phase 1: Read

Extract every term in the offer. List anchors, hedging, urgency signals, omissions. Do not interpret yet.

Phase 2: Analyze

Map ZOPA, BATNA, information asymmetry, value gap. Quantify the gap in dollars before any qualitative language. See references/skills.md Skill-Negotiation-001.

Phase 3: Design

Draft PCP framing (Perception, Context, Permission) before producing a number. Whoever defines the frame controls the negotiation. See Skill-Negotiation-003.

Phase 4: Assess

Run the invisible-disadvantage check. Compare risk of countering vs. accepting. Apply the anchor-first decision rule (Skill-Negotiation-008) and BATNA discipline (Skill-Negotiation-009).

Phase 5: Review

Produce a DRAFT counter with explicit human approval gate. Specific closing pattern from Skill-Negotiation-010 applies once verbal agreement is reached.

Verification

Output is acceptable when ALL of the following hold:

Offer net value, achievable value, and gap are quantified in dollars (Skill-Negotiation-001 implementation block).
At least one written-signal observation from Skill-Negotiation-007 is cited if the offer arrived in writing.
Counter-proposal carries PCP framing in the output, not just a number (Skill-Negotiation-003).
BATNA worksheet (Skill-Negotiation-009) is filled before the first counter goes out.
Bundling rule (Skill-Negotiation-005) is honored: no single-dimension concession appears in the counter.
Final output is marked DRAFT and waits for explicit human approval before sending.
If routed through an agentic system, the negotiation analysis runs on a senior-tier model (Skill-Negotiation-006).

Read the full file on GitHub · 131 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

references/skills.md 12 KB

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.

6d ago First seen · 131 lines · 78 tokens per session scan A 9753ad450c2b

Subscribe to this mod's changes

negotiation is a skill published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,254 once invoked, about $0.0004 per session on Opus 5. 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 2026-09-03.

CI and CD Finance and fintech Planning agentic-ai ai-agents ai-assistant anthropic-claude automation

stock-analyzer

A comprehensive stock deep analysis tool that combines real-time quotes, fundamental metrics, technical indicators, and growth analysis into a single professional report. Supports A-share, US stocks, HK stocks. Generates detailed investment recommendations with risk assessment and actionable trading strategies.

netease-youdao/LobsterAI · 53 tokens

negotiation