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 fatihguner/foreman --skill reading-peoplegit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/reading-people)<a href="https://agentmods.dev/skills/fatihguner/foreman/reading-people"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/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.
<a href="https://agentmods.dev/skills/fatihguner/foreman/reading-people"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/reading-people.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.04027 |
| Opus 5 | $0.00056 | $0.02014 |
| Sonnet 5 | $0.00022 | $0.00805 |
| Haiku 4.5 | $0.00011 | $0.00403 |
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 6d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Reading People
The claim that words account for only 7% of communication is exaggerated -- but the belief that they account for 100% is far more dangerous.
Albert Mehrabian's 1967 research produced the famous 55/38/7 formula: 55% body language, 38% tone, 7% words. The study's conditions were narrow (single-word emotional statements), and the numbers should not be taken as universal law. What should be taken as universal law is the underlying insight: a substantial majority of what people communicate has nothing to do with the sentences they construct. Founders who listen only to words are reading a transcript when they should be watching a film. The investor who says "interesting" while leaning back with crossed arms is not interested. The hire who says "I'm excited" while avoiding eye contact is not excited. The customer who says "we'll think about it" while checking the time has already decided.
Reading people is not mind-reading. It is pattern recognition -- the trained habit of observing behaviour that most professionals ignore because they were never taught to look.
The Framework
Reading people operates through five interlocking skills, each progressively more difficult to master.
Skill 1: Stop Waiting to Talk
The precondition for reading people is the ability to stop composing your next sentence while someone else is speaking. Most people do not listen; they queue their response. The internal experience feels like listening -- you are facing the speaker, you are nodding -- but the cognitive bandwidth allocated to comprehension is minimal because most of it is consumed by rehearsal.
Gerald Bell of the Bell Leadership Institute prescribes the Achiever Listening Position: sit up straight, lean slightly forward, arms at your sides, eyes fixed on the speaker with the intensity of a child watching television. The physical posture forces cognitive engagement. When the mind wanders -- and it will -- the posture serves as an anchor to pull attention back to the speaker.
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.
- 6d ago First seen · 220 lines · 112 tokens per session scan A 6a71e6721960
reading-people is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 7d ago), licensed MIT. It adds 112 tokens to every session and 4,027 once invoked, about $0.0006 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 2026-09-06.
Other skills, from other repositories
learn
Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmortem and /evolve…
zapier-demo
Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up…
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
explain
Explain jig vocabulary and artifacts in plain language. Three modes: term mode defines one lexicon term; artifact mode walks through a spec or ADR and its linked references; passage mode explains pasted jig output. Output is ephemeral (chat-only). Auto-triggers when you say explain this term, walk me through this…
matlab-create-live-script
Create, edit, and run plain-text MATLAB live scripts (.m files) with rich text formatting, LaTeX equations, section breaks, and inline figures. Use when generating tutorials, analysis notebooks, reports, documentation, or educational content, when modifying existing live scripts, or when converting existing binary…
economics
Runtime subject skill payload for economics subject activation.