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.
npx skills add fatihguner/foreman --skill competitive-negotiationgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/skills/fatihguner/foreman/competitive-negotiation)<a href="https://agentmods.dev/skills/fatihguner/foreman/competitive-negotiation"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/competitive-negotiation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.05065 |
| Opus 5 | $0.00051 | $0.02533 |
| Sonnet 5 | $0.00021 | $0.01013 |
| Haiku 4.5 | $0.00010 | $0.00507 |
Grade A, and why
competitive-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 2d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Competitive Negotiation
The vice president of sales at a technology company ran an experiment. His team had been discounting reflexively -- shaving margins to close deals, training customers to expect that the quoted price was fiction. He instructed every sales professional to add 10 percent to their next proposal. The team protested: the market was saturated, the product was ageing, proposals went through competitive RFP processes. Four months later, the results arrived. Profitability increased 3 percent. Sales volume did not decrease at all. No new product. No new marketing. No market shift. The only variable that changed was the number on the opening offer. The most important moment in any competitive negotiation is the moment of asking -- and most people retreat at precisely that point, bargaining themselves down before the other party has said a word.
The Framework
The Nature of Competitive Negotiation
Competitive negotiation is the process by which parties determine who gets how much of a defined pool of value. It answers a single question: how will this fixed pie be divided? Unlike cooperative negotiation -- which seeks to expand the pie (see Win-Win Negotiation for the principled approach, and Negotiation Game Theory for the mathematical structure) -- competitive negotiation accepts the pie's current size and focuses entirely on claiming a favourable share.
Eight characteristics make the process predictable:
- Fixed pie assumption. The total value under negotiation is treated as finite. One party's gain is the other's loss.
- Zero-sum exchange. Every dollar, percentage point, or term improvement for one side comes at the other's expense.
- Positional bargaining. Each party states a position and defends it through a series of calculated retreats.
- Concession sequences. Without concessions from both sides, no agreement is possible. The pattern of concessions is the negotiation.
- Diminishing increments. Early moves are large; later moves shrink. The first concession might be thousands; the last might be a set of floor mats.
- Midpoint gravity. Outcomes gravitate toward the midpoint of the first two reasonable offers. This is the single most exploitable feature of the process.
- The dance cannot be skipped. Attempting to "cut to the chase" with a fair offer at the outset resets the anchor against you. The right answer at the wrong time is the wrong answer.
- Rising tension. As concessions shrink and the gap narrows, emotional pressure increases. The negotiator who keeps composure captures the final increments.
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.
- 2d ago Changed · +239 lines · +103 tokens per session ac94f9cfa7d9
- 8d ago First seen · 1 lines · 0 tokens per session scan A 3a8d19ebb3ba
competitive-negotiation is a skill published in the GitHub repository fatihguner/foreman (47 stars, last pushed 3d ago), licensed MIT. It adds 103 tokens to every session and 5,065 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
Negotiation Expert
Negotiation Expert delivers practical business output with market context, metrics, stakeholder clarity, and execution focus.
apply-ackerman-bargaining
Use when negotiating a price and a single opening offer plus ad hoc counters isn't converging efficiently — set a target price, open with an anchor around 65% of it, make three further offers at roughly 85%, 95%, and a final non-round number at target, using a calibrated question between each offer and shrinking…
restaurant-pricing
Competitive pricing analysis — compares menu prices against local competitors, identifies underpriced items leaving money on the table and overpriced items hurting sales.
pricing-negotiation
Handles pricing conversations and discount requests using proven negotiation frameworks and scripts.
negotiation-advisor
Interactive negotiation coach for pricing conversations, discount pushback, and multi-stakeholder deal dynamics.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.