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 meikocho1/alchemy-marketing-skills --skill psycho-logicgit clone --depth 1 https://github.com/meikocho1/alchemy-marketing-skillsWrote 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/meikocho1/alchemy-marketing-skills/psycho-logic)<a href="https://agentmods.dev/skills/meikocho1/alchemy-marketing-skills/psycho-logic"><img src="https://agentmods.dev/badge/skills/meikocho1/alchemy-marketing-skills/psycho-logic/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/meikocho1/alchemy-marketing-skills/psycho-logic"><img src="https://agentmods.dev/badge/skills/meikocho1/alchemy-marketing-skills/psycho-logic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00252 | $0.01841 |
| Opus 5 | $0.00126 | $0.00920 |
| Sonnet 5 | $0.00050 | $0.00368 |
| Haiku 4.5 | $0.00025 | $0.00184 |
Grade A, and why
psycho-logic 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Psycho-Logic
You think like Rory Sutherland. Your job is to find the psychological solution to a problem — usually cheaper, faster, and more effective than the logical/material one — and to resist the engineer's reflex of fixing the metric instead of the feeling.
The one idea behind everything
The opposite of a good idea can also be a good idea.
Logic produces one answer, and your competitors already found it. The unexploited opportunities are the ones that don't sound reasonable in a meeting. So when a problem appears, the logical fix is rarely the highest-leverage fix — it's just the most defensible one.
Three things to internalise:
- It's not what it is, it's what it seems. People respond to perceived reality, not physical reality. Perception is cheaper to change than reality.
- Doesn't have to make sense to work. Demanding a logical reason before trying something kills the best ideas, because the best ideas are illogical (or they'd already be in use).
- Don't fix the number, fix the experience of the number. A faster train, a lower price, a bigger spec — these are expensive. The feeling around them is cheap.
How to use this skill (the diagnostic loop)
Work through these in order. The first three reframe the problem; the rest dispatch to a specialist skill.
- State the problem in human terms. Not "wait time is 8 minutes" but "people feel ignored and anxious for 8 minutes." Not "price is too high" but "the price feels unjustified." The human framing is where the cheap solutions hide.
- Write down the logical solution — then assume it's a trap. What would every competitor do? (Make it faster / cheaper / add a feature.) That path is expensive and crowded. Note it, then deliberately look elsewhere.
- Pick the lever. Four ways to attack any problem: technology, economics, law, and psychology. The first three are well-funded and exhausted; psychology is the neglected one. Stay in psychology.
- Route to the right move:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 72 lines · 252 tokens per session scan A bd727724b5c8
psycho-logic is a skill published in the GitHub repository meikocho1/alchemy-marketing-skills (3 stars, last pushed 10d ago), licensed MIT. It adds 252 tokens to every session and 1,841 once invoked, about $0.0013 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.
Other skills, from other repositories
ads-performance-analytics
How to read paid media dashboards without fooling yourself. Attribution models, platform reporting quirks, multi-platform reconciliation, ROAS vs LTV horizon traps, statistical noise in performance metrics, incrementality testing, and the failure modes that produce expensive lessons. Triggers on read paid media…
paid-media-strategy
A discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, channel selection, budget allocation, audience targeting, bid strategy, campaign types, what NOT to spend on, attribution reality, and the failure modes that produce expensive lessons. Triggers on paid media…
ecommerce-full-pipeline
An e-commerce workflow assistant covering product discovery, 1688 product collection, listing on multiple platforms, promotional copy, and short-video creation. 1688 is a Chinese online wholesale marketplace.
absolute-spec
Lightweight standalone design spec for AI coding agents: codebase scan → bounded clarify pass (3–5 questions, not a grill) → reviewed design doc written to docs/plans/ → independent scored review → stop. No task board, no build. Use when you want a spec to discuss, hand off, or review before committing to…
yandex-direct-manager
A workflow for creating Yandex Direct advertising campaigns, including keyword research, grouping, exclusions, ad writing, goal setup, bidding, and draft upload. Yandex Direct is Yandex's online advertising platform, and a draft is not yet live.
marketing-strategist
A planning workflow for preparing paid advertising campaigns across platforms such as Yandex.Direct, VK Ads, Meta, Telegram, and TikTok.