agentmods.dev

walk-away-power

walk-away-power is a skill for Claude Code, Codex from YannisKiefer/dark-psychology-skills. It costs 22 tokens per session (357 once invoked), scanned A, original, MIT.

A guide to ending a negotiation or conversation when the terms, behaviour, or request are unacceptable. It describes short, polite exits as well as firmer boundaries for abusive, fraudulent, or illegal situations.

In plain words
What is it for?
Use it to handle impossible prices, rude buyers, stalled conversations, suspected scams, and requests you cannot ethically or legally accept.
Why use it?
It helps you leave a deadlocked or unsafe discussion without prolonging the argument or making unnecessary commitments.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 19repo +1 2mo ago A scan 22 tokens original MIT

Good fit Use it to handle impossible prices, rude buyers, stalled conversations, suspected scams, and requests you cannot ethically or legally accept.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yanniskiefer/dark-psychology-skills/walk-away-power
View source ↗ YannisKiefer/dark-psychology-skills
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 YannisKiefer/dark-psychology-skills --skill walk-away-power
Clone the repo
git clone --depth 1 https://github.com/YannisKiefer/dark-psychology-skills

Made for: Claude Code, Codex.

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.

agentmods badge for walk-away-power

README.md
[![agentmods](https://agentmods.dev/badge/skills/yanniskiefer/dark-psychology-skills/walk-away-power/github.svg)](https://agentmods.dev/skills/yanniskiefer/dark-psychology-skills/walk-away-power)
Your own site
<a href="https://agentmods.dev/skills/yanniskiefer/dark-psychology-skills/walk-away-power"><img src="https://agentmods.dev/badge/skills/yanniskiefer/dark-psychology-skills/walk-away-power/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.

agentmods 80×15 button for walk-away-power

Your own site · 80×15
<a href="https://agentmods.dev/skills/yanniskiefer/dark-psychology-skills/walk-away-power"><img src="https://agentmods.dev/badge/skills/yanniskiefer/dark-psychology-skills/walk-away-power.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 357 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00357
Opus 5.5 $0.00009 $0.00143
Sonnet 5.5 $0.00004 $0.00071
Haiku 4.5 $0.00002 $0.00036

Measured 2mo ago against content hash 9679ace21fc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

walk-away-power 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.

skills/walk-away-power/SKILL.md · 51 lines

What it actually says

Walk-Away Power

The Big Idea

Being able to leave beats any argument.

Buyers smell a bluff. Real walk power comes from having other deals.

Never walk as punishment. Insulted people take revenge.

The Moves

  1. Check before you leave. Deadlock or just fear, timing, money trouble? Try ONE question first: "What would need to change for this to work?"

  2. The soft exit (decent person, bad fit): "No stress, this month is full anyway. If it matters again, I'm easy to find." One message. Then stop writing first.

  3. The strong walk (terms impossible): "That number doesn't work for what this takes. I'd rather tell you straight than do it half-way." This one converts weeks later. You become the vendor who said no nicely.

  4. The hard exit (abuse, scams, illegal asks): "Not something I can help with. Good luck." No lectures. The exit IS the boundary.

  5. Two lines max on any goodbye. Long goodbyes read as hurt.

  6. Your goodbye gets screenshots too. It must look clean forwarded by someone who dislikes you.

When It Backfires

  • Threatening to walk for discounts. Called bluffs end deals and status.
  • Walking angry. Wait ten minutes, then decide.
  • Coming back later at a discount. Full price or not at all.

One-Line Memory

One warm no teaches everyone your terms are real.

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.

  1. 2mo ago First seen · 51 lines · 22 tokens per session scan A 9679ace21fc5

Subscribe to this mod's changes

walk-away-power is a skill published in the GitHub repository YannisKiefer/dark-psychology-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 357 once invoked, about $0.0001 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.

Claude CodeMarketing and SEOagent-skillsai-agentsdark-psychologynegotiationpersuasion
Related

walk-away-power compared with skills from other repositories

walk-away-power next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
walk-away-powerYannisKiefer/dark-psychology-skillsSkill192mo agoMITA22Claude Code, Codex
cialdini-influencefatihguner/foremanSkill632mo agoMITA88Claude Code
persuasion-and-influencefatihguner/foremanSkill632mo agoMITA101Claude Code
apply-door-in-the-facejeffreytse/grimoire-coreSkill621d agoMITA76Claude Code
reciprocity-strategy-designerbookforge-ai/bookforge-skillsSkill426mo agoCC-BY-SA-4.0A127Claude Code
procurementericrisco/rsc-harnessSkill5032d agoMITA92Claude Code, Codex
convert-three-locksFerroxLabs/waylandSkill6177d agoAGPL-3.0A108Claude Code, Codex