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 Doris-Labs/sales-skills --skill negotiationgit clone --depth 1 https://github.com/Doris-Labs/sales-skillsWrote 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/doris-labs/sales-skills/negotiation)<a href="https://agentmods.dev/skills/doris-labs/sales-skills/negotiation"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/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.
<a href="https://agentmods.dev/skills/doris-labs/sales-skills/negotiation"><img src="https://agentmods.dev/badge/skills/doris-labs/sales-skills/negotiation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00074 | $0.01493 |
| Opus 5.5 | $0.00030 | $0.00597 |
| Sonnet 5.5 | $0.00015 | $0.00299 |
| Haiku 4.5 | $0.00007 | $0.00149 |
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 2mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Negotiation
Purpose
Get a deal closed on terms you can defend without eroding price. Every concession is traded for something that improves the deal — never given to "get to yes."
Inputs
- The specific ask (discount %, terms, what the buyer wants)
- Deal value, products/SKUs in play, and your floor (walk-away price/terms)
- The value drivers and pains already established — your leverage to re-sell
- Open objections and what the buyer has already committed to
Method
- Diagnose before you respond. Don't react to the number. Find out why: is it budget, a competing quote, internal approval theater, or a test? The right response differs for each. Ask: "Help me understand — is this a budget ceiling, or are you comparing against another option?"
- Anchor first, anchor high. Whoever frames the number first sets the range. Lead with full price tied to the value/ROI you established — never open with a discount. If they anchor low, re-anchor to value before discussing the gap; don't negotiate against their number.
- Trade, don't cave. Never give a concession without getting something back. The rule is "If… then…": "If you can do X, then I can do Y." A unilateral discount trains the buyer that your price is fiction and that pushing harder pays.
- Re-sell value to protect price. Before conceding a cent, return to the cost of the problem and the value of the outcome. Reframe price as a fraction of the value delivered: "The discount you're asking for is $Z; the problem we discussed is costing you $Z every month." Make price feel small against the stakes.
- Climb the concession ladder. When you must move on price, extract value in
return, working from cheapest-for-them to most valuable-for-you. Ask for these
(roughly in order):
- Longer term length — multi-year commitment for the discount
- Upfront / annual payment — paid annually or in advance, not monthly
- Case study / logo rights — public reference or quote
- References / intros — referenceable calls, intro to other teams/divisions
- Expansion commitment — committed path to more seats/products/usage Give the smallest price move that closes, and only in exchange for a rung.
- Recognize manufactured urgency. "We need a decision by Friday" is often a tactic to pressure a discount. Test it: "What happens Friday?" If the deadline is real (board approval, fiscal year), it's leverage you can trade against. If it evaporates under one question, it's manufactured — don't pay for a fake clock.
- Plan give/gets before the call. Map every concession to its return. Never improvise a discount live.
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.
- 2mo ago First seen · 112 lines · 74 tokens per session scan A 6da20e9e9afd
negotiation is a skill published in the GitHub repository Doris-Labs/sales-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 74 tokens to every session and 1,493 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
negotiation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| negotiationDoris-Labs/sales-skills | Skill | 3 | 5mo ago | MIT | A | 74 | Claude Code |
| lynquGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 40 | Claude Code, Codex |
| lynqu-sales-followupGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 39 | Claude Code, Codex |
| lynqu-deal-deskGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 48 | Claude Code, Codex |
| lynqu-event-blitzGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 47 | Claude Code, Codex |
| lynqu-lead-managementGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 40 | Claude Code, Codex |
| lynqu-outreachGravisun/lynqu-ai-toolkit | Skill | 6 | 11d ago | none | A | 41 | Claude Code, Codex |