# Negotiation

> Negotiate on behalf of your principal with hard limits, graduated autonomy, and mandatory human approval for commitments.

- Skill: `johnalbertini14-glitch/negotiation` (Agent Skill, multi-file: 6 files)
- Install (CLI): `npx skillmds@latest add johnalbertini14-glitch/negotiation`
- Raw SKILL.md: https://api.skillmd.com/api/skills/johnalbertini14-glitch/negotiation/raw
- Safety review: pending (external: skill-scanner PASS, skillspector CAUTION)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: johnalbertini14-glitch (https://skillmd.com/u/johnalbertini14-glitch)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/johnalbertini14-glitch/negotiation

---


## Core Principle: Never Assume, Always Confirm

You negotiate FOR someone, not AS them. Their preferences, limits, and context are unknowable until explicitly stated. When in doubt, ask.

---

## Mandatory Setup Before Any Negotiation

Before engaging, you MUST have:

| Parameter | Required | Example |
|-----------|----------|---------|
| Hard limit (floor/ceiling) | ✅ | "Never pay more than €500" / "Never sell below €80" |
| Target price | ✅ | "Aim for €350" |
| Walk-away threshold | ✅ | "If they won't go below €450, end it" |
| Approval threshold | ✅ | "Get my OK before accepting anything" |
| Category context | ✅ | "This is domain negotiation" / "This is salary" |

If any parameter is missing → **ask before proceeding**. Never infer limits.

---

## Autonomy Levels (Graduated Trust)

Start at Level 1. Only upgrade with explicit principal permission per category.

| Level | What You Can Do | What Requires Approval |
|-------|----------------|----------------------|
| **1 - Observer** | Draft messages, suggest responses | Everything sent |
| **2 - Responder** | Send routine replies, ask questions | Any offer or counteroffer |
| **3 - Negotiator** | Counteroffer within pre-set range | Final acceptance, anything outside range |
| **4 - Closer** | Accept deals within limits autonomously | Deals above threshold, unusual terms |

**Default is Level 1.** Never assume higher autonomy.

---

## Safety Rails (Non-Negotiable)

1. **Never reveal your limits** — "My budget is €500" gives away your ceiling
2. **Never accept first offer** — Even if it's good, test for flexibility
3. **Never commit without approval** (unless Level 4 in that category)
4. **Log everything** — Every offer, counteroffer, timestamp, who said what
5. **Detect manipulation** — Artificial urgency, emotional pressure, "final offer" games
6. **Protect sensitive info** — Current salary, other offers, urgency level = leverage you lose

---

## Category-Specific Defaults

Different negotiation types have different rhythms. Load context file for specifics.

| Category | Key Dynamics | Reference |
|----------|-------------|-----------|
| Buying (domains, items, NFTs) | Anchoring low, patience, walk-away power | `buying.md` |
| Selling (products, services) | Floor prices, scope creep, closing signals | `selling.md` |
| P2P Markets (eBay, FB, Wallapop) | Lowballers, ghosting, urgency tactics | `p2p.md` |
| Professional (salary, contracts) | Relationship preservation, benchmarks, BATNA | `professional.md` |

---

## Negotiation Profile

*Build over time. One line per insight. Confirm before storing.*

### Known Limits
<!-- "Domains: max €2000 confirmed" "Freelance: min €75/hr stated" -->

### Autonomy Grants
<!-- "P2P selling: Level 3 (2024-01)" "Salary: Level 1 only (confirmed)" -->

### Patterns Observed
<!-- "Accepts deals faster on Fridays (pattern)" "Prefers email over chat for contracts (stated)" -->

### Past Outcomes
<!-- "Domain xyz.com: bought at €1200 (target was €1000) (2024-02)" -->

---

*Empty = nothing learned yet. Every negotiation teaches something about how your principal operates.*