agentmods.dev

dark-tactics-defense

dark-tactics-defense is a skill for Claude Code, Codex from YannisKiefer/dark-psychology-skills. It costs 25 tokens per session (415 once invoked), scanned A, original, MIT.

A guide for recognizing manipulation tactics such as fake urgency, guilt, escalating requests, and attempts to isolate you from advice. It also describes ways to keep your own communication honest.

In plain words
What is it for?
Use it to examine conversations, offers, negotiations, or sales messages for warning signs and choose a calmer response.
Why use it?
It helps you slow down and check claims when someone is trying to pressure, confuse, or control a decision.

Skill for Claude CodeCodex

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

not rated 19repo +1 2mo ago A scan 25 tokens original MIT

Good fit Use it to examine conversations, offers, negotiations, or sales messages for warning signs and choose a calmer response.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yanniskiefer/dark-psychology-skills/dark-tactics-defense
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 dark-tactics-defense
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 dark-tactics-defense

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yanniskiefer/dark-psychology-skills/dark-tactics-defense"><img src="https://agentmods.dev/badge/skills/yanniskiefer/dark-psychology-skills/dark-tactics-defense.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 415 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 $0.00025 $0.00415
Opus 5.5 $0.00010 $0.00166
Sonnet 5.5 $0.00005 $0.00083
Haiku 4.5 $0.00003 $0.00042

Measured 2mo ago against content hash e14126ef284f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dark-tactics-defense 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/dark-tactics-defense/SKILL.md · 55 lines

What it actually says

Dark Tactics Defense

The Big Idea

All of dark psychology fits in one line: people only defend against what they can see.

Pros hide the mechanism. Your job is to see it.

And for your own side: use only moves that survive being explained out loud.

The Trick List (so you can spot it)

  1. Fake scarcity: "only 2 left", every week again
  2. Small gift first, big ask after
  3. Scare first, sell the rescue after
  4. Tiny yes, then bigger and bigger yeses
  5. Hot and cold attention that trains you to chase
  6. Guilt: "after all I did for you..."
  7. "Don't tell your partner or lawyer about this"
  8. Word floods that sound smart and stop thinking
  9. "Either this or disaster"
  10. Making you doubt what you clearly saw

The Defense

  1. Never decide on someone else's clock. Rushed = slow down.
  2. Get it in writing.
  3. Keep your advisors close. Anyone who cuts them off is not on your side.
  4. Ask for specifics. "What exactly does guaranteed mean?"
  5. One sign means little. Two or more mean slow down.
  6. A bad feeling without proof? Check before you trust or spend.

The Honest Line (for your own moves)

Use freely. Works even when explained: real proof, real deadlines, true numbers, named flaws, earned discounts, freedom to walk, freedom to ask anyone.

Never touch. Always explodes later: invented results, fake urgency, fake reviews, switch after sale, fake titles, guilt trips, cutting people off from advisors.

The test: if they found out exactly what you did, angry or impressed?

One-Line Memory

Honest influence keeps working after you explain it. Tricks only work until they're seen.

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 · 55 lines · 25 tokens per session scan A e14126ef284f

Subscribe to this mod's changes

dark-tactics-defense is a skill published in the GitHub repository YannisKiefer/dark-psychology-skills (19 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 415 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 CodeSecurityagent-skillsai-agentsdark-psychologynegotiationpersuasion
Related

dark-tactics-defense compared with skills from other repositories

dark-tactics-defense next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dark-tactics-defenseYannisKiefer/dark-psychology-skillsSkill192mo agoMITA25Claude 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