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 marcos-sponton/frameworks-as-skills --skill never-split-the-differencegit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/never-split-the-difference)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/never-split-the-difference"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/never-split-the-difference/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/marcos-sponton/frameworks-as-skills/never-split-the-difference"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/never-split-the-difference.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 | $0.00279 | $0.03533 |
| Opus 5 | $0.00139 | $0.01767 |
| Sonnet 5 | $0.00056 | $0.00707 |
| Haiku 4.5 | $0.00028 | $0.00353 |
Grade A, and why
never-split-the-difference 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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Never Split the Difference — Chris Voss's Black Swan Method
Chris Voss is the former lead international kidnapping negotiator for the FBI (24 years) and founder of the Black Swan Group. His 2016 book Never Split the Difference: Negotiating As If Your Life Depended On It reorganized modern negotiation practice around tactical empathy — treating the counterpart's emotional world as information to be extracted, not as an obstacle to be argued past. The method carries the vocabulary of hostage crisis into every negotiation, from procurement to salary to family. This skill also captures post-book refinements from Voss's MasterClass, The Full Fee Agent (2022, with Steve Shull), the Black Swan Group's Negotiation Mastery Newsletter, and long-form podcast appearances (Lex Fridman #364, Diary of a CEO, Jordan Harbinger).
Voss's method is opinionated because the stakes were. It consistently contradicts negotiation defaults: split-the-difference compromise, chase-the-yes, deploy-BATNA, be-reasonable-early, ask-why. When the assistant applies this skill, the answers should feel like Voss's own way of thinking — script-specific, calm, low-and-slow, empathy-first.
When this skill activates
Use this skill when the user is:
- Preparing for a salary, comp, or promotion conversation.
- Negotiating a vendor / procurement / commercial-terms deal (pricing, T&Cs, SLAs, penalties).
- Defending price against a discount request or trying to hold the full fee.
- Preparing to deliver bad news, a hard no, or a walk-away.
- In a stalled negotiation where the counterpart has gone silent or given an ultimatum.
- Trying to defuse an accusatory or hostile counterpart before making an ask.
- Trying to uncover what the counterpart actually cares about (Black Swans) rather than what they say they care about.
- Doing an M&A or partnership terms negotiation.
- Drafting an email, script, or call plan that has to persuade under pressure.
- Coaching someone through a difficult conversation (with a client, a boss, a co-founder, a partner).
- Explicitly reaching for a compromise / split-the-difference / "let's meet in the middle" move — this skill exists to push back on that reflex.
What ships with it
12 files 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.
- evals/evals.json 12 KB
- examples/.gitkeep 0 B
- README.md 6.1 KB
- references/applications.md 13 KB
- references/author-live-sources.md 9.7 KB
- references/examples.md 17 KB
- references/heuristics.md 22 KB
- references/method.md 19 KB
- references/post-book.md 15 KB
- references/prompts.md 12 KB
- references/sources.md 9.3 KB
- references/voice-and-tone.md 16 KB
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.
- 8d ago First seen · 115 lines · 279 tokens per session scan A 549293f47a60
never-split-the-difference is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 279 tokens to every session and 3,533 once invoked, about $0.0014 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 2026-08-31.
Other skills, from other repositories
acquire-skills
Find and install skills for what you're doing — tech or reasoning gaps. Matches activity and tech context to relevant skills. Use when entering unfamiliar tech, stuck on a reasoning challenge, or no skill fits.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
endpoint-discovery
Discovers URLs, endpoints, and paths from web applications using katana, gospider, and gau. Use when needing to enumerate application endpoints, find hidden paths, gather historical URLs, or map web application structure during reconnaissance.
param-miner
Discover hidden HTTP parameters in web applications that could reveal hidden functionality or vulnerabilities. Use when testing APIs, when looking for hidden parameters like admin or debug, or when the user mentions parameter discovery.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.