reading-people

reading-people is a skill for Claude Code, Codex from YannisKiefer/dark-psychology-skills. It costs 28 tokens per session (432 once invoked), scanned A, original, MIT.

A conversation guide for judging someone’s likely intentions from their writing patterns, questions, timing, and reactions. It focuses on testing assumptions and spotting pressure or manipulation.

In plain words
What is it for?
Use it to interpret uncertain replies, ask clarifying yes-or-no questions, identify warning signs, and respond to anger or evasiveness.
Why use it?
It helps separate what someone says from possible concerns such as fear, hesitation, or an attempt to rush you.

Skill for Claude CodeCodex

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

Good fit Use it to interpret uncertain replies, ask clarifying yes-or-no questions, identify warning signs, and respond to anger or evasiveness.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yanniskiefer/dark-psychology-skills/reading-people"><img src="https://agentmods.dev/badge/skills/yanniskiefer/dark-psychology-skills/reading-people.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 432 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 $0.00028 $0.00432
Opus 5 $0.00014 $0.00216
Sonnet 5 $0.00006 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured 12d ago against content hash 96bbf59c8ebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reading-people 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 12d 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/reading-people/SKILL.md · 58 lines

What it actually says

Reading People

The Big Idea

Words lie fast. Patterns lie slow.

Watch rhythm, message length, and timing changes. Not the words.

The Moves

  1. Learn their normal first. How does THIS person usually write? Speed, length, style. A sudden change means something happened. Find out before you react.

  2. The yes/no test. Ask a question with two possible answers. Anything except yes or no IS the answer: "Did you look at it?" ... "It's interesting..." = they didn't look.

  3. Silence means almost nothing. Silence fits every story: busy, shopping rivals, scared, gone. Don't guess. Collect one fact instead: "Is it price, trust, or timing?"

  4. Catch the objection before they say it. Hedging and topic switches mean an objection is forming. Answer it now. Once spoken, people defend it forever.

  5. Anger is pain in a costume. Rude messages usually mean: burned before, embarrassed, scared. Answer the pain. Never the anger. Logic on an angry person adds fuel.

  6. Tricks aimed at YOU:

    • Rush clocks: "decide in 1 hour"
    • Small gift first, big ask after
    • "Don't tell your partner or lawyer"
    • Many questions from them, zero answers to you
    • Guilt flips: suddenly you owe them Two of these together? Slow down. Check facts yourself.
  7. The screenshot test. Write every message like it gets forwarded to a lawyer. Sometimes it is.

When It Backfires

  • Reading one signal as proof. Wait for patterns.
  • Believing someone else's label ("he's a tire kicker"). Judge fresh.

One-Line Memory

When someone pushes speed at you, that's when you slow down.

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. 12d ago First seen · 58 lines · 28 tokens per session scan A 96bbf59c8ebe

Subscribe to this mod's changes

reading-people is a skill published in the GitHub repository YannisKiefer/dark-psychology-skills (5 stars, last pushed 17d ago), licensed MIT. It adds 28 tokens to every session and 432 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

cialdini-influence

Applies Cialdini's seven principles of ethical persuasion -- Reciprocity, Commitment and Consistency, Social Proof, Authority, Liking, Scarcity, and Unity -- to business contexts including sales, marketing, fundraising, and negotiation. Use when designing conversion funnels, optimizing sales processes, preparing…

fatihguner/foreman · 88 tokens

persuasion-and-influence

Equips leaders with daily micro-influence tactics -- reading emotional temperature in meetings, deploying peer power, establishing authority organically, using consistency commitments, and knowing when to compromise. Use when preparing for a difficult one-on-one, navigating a meeting where buy-in is needed, responding…

fatihguner/foreman · 101 tokens

reciprocity-strategy-designer

Design reciprocity-based persuasion strategies and detect when reciprocity is being used against you. Use this skill when planning give and take strategies, creating lead magnets or free value offers, designing favor-first or value-first outreach, building gift-based marketing campaigns, crafting free samples or free…

bookforge-ai/bookforge-skills · 127 tokens

procurement

Use when a small operator must choose what to buy and from whom: pick a supplier, write an RFI/RFQ/RFP that returns comparable bids, score quotes on total cost of ownership, negotiate price and payment terms, or judge single-source risk. NOT redlining the purchase agreement (that is contracts), NOT the price you…

ericrisco/rsc-harness · 92 tokens

delivering-the-deal

Provides the complete execution toolkit for closing negotiations: a 21-point preparation checklist, a framework for overcoming obstacles and disarming tactics, and the three-part satisfaction model for durable agreements. Includes a self-assessment instrument for measuring negotiation competence. Use when preparing…

fatihguner/foreman · 92 tokens

competitive-negotiation

Executes the competitive negotiation process from opening move through final concession: anchoring strategy, ambitious asking, concession architecture, midpoint management, impasse-breaking through linkage, and closing discipline. Provides actionable protocols for value-claiming negotiations. Use when setting price in…

fatihguner/foreman · 103 tokens