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 reader-psychologygit 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/reader-psychology)<a href="https://agentmods.dev/skills/fatihguner/foreman/reader-psychology"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/reader-psychology/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/reader-psychology"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/reader-psychology.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 | $0.00085 | $0.04768 |
| Opus 5 | $0.00043 | $0.02384 |
| Sonnet 5 | $0.00017 | $0.00954 |
| Haiku 4.5 | $0.00009 | $0.00477 |
Grade A, and why
reader-psychology 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 — 206 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.
Reader Psychology
F-PATTERN. Eye-tracking research reveals that readers do not read -- they scan in an F shape, spending most attention on the first two lines and the left margin. Everything else is a gamble. Psychologist George Miller's landmark study established that human working memory holds approximately seven items, plus or minus two, at any given moment. Between that hard cognitive ceiling and the 121 emails the average manager receives daily, the arithmetic is unforgiving: every sentence a writer produces competes against a reader's finite neural budget. Understanding that budget -- its size, its depletion rate, its failure modes -- is the prerequisite for writing that actually gets through.
The Framework
The Busy Brain: Three Constraints
The limited capacity of the human attention system produces three consequences that shape every act of reading.
Constraint 1: We Cannot Process Everything in Front of Us
At any moment, the brain confronts more information than it can absorb. Its attention system responds by acting as a filter -- selecting what to notice and suppressing the rest. A 1999 Harvard study demonstrated this vividly: when participants were asked to count basketball passes in a video, nearly half failed to notice a person in a gorilla costume strolling through the scene. The brain's suppression of irrelevant stimuli is so aggressive that even conspicuous objects vanish when they fall outside the current focus. For writers, the implication is stark: information that is present in a message but not actively foregrounded may as well not exist.
Constraint 2: Focus Exhausts Quickly
Directing attention is effortful, and the resource depletes faster than most people assume. In a study by psychologist Brandon Schmeichel, participants who spent six minutes resisting the urge to look at flashing words on screen subsequently scored 20% lower on a graduate-level reading comprehension test. Six minutes of attentional control was enough to measurably impair later cognitive performance. Physical fatigue compounds the effect -- athletes under physical exhaustion show impaired attention and decision-making, and information scientist Gloria Mark found that workers need an average of 23 minutes to fully return to a task after a single interruption. One study estimated that minds wander a full third of the time while people attempt to read, with the rate climbing further when the material is complicated.
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 · 206 lines · 85 tokens per session scan A eaadd96a6210
reader-psychology is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 85 tokens to every session and 4,768 once invoked, about $0.0004 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
simple-man
High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or low-cognitive-load collaboration without reducing effort, validation, proactivity, or accuracy. Do not use when the user asks for a tutorial…
simple-man
High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or low-cognitive-load collaboration without reducing effort, validation, proactivity, or accuracy.
caveman
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
curiosity-gap-architect
Build an Unexpected hook for a message, pitch, essay, ad, talk, or email — first break the audience's expected pattern to CAPTURE attention, then open a curiosity gap (a knowledge gap they didn't know existed) to HOLD attention all the way to the core message. Use this skill whenever the user says 'how do I hook…
simple-man
High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or low-cognitive-load collaboration without reducing effort, validation, proactivity, or accuracy. Do not use when the user asks for a tutorial…
simple-man
High-compression professional communication mode. Use when the user wants fewer tokens, less reading, no filler, compact coding-agent status, terse technical answers, or low-cognitive-load collaboration without reducing effort, validation, proactivity, or accuracy. Do not use when the user asks for a tutorial…