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 agentmods add skills/deciqai/knowledge-skills/bayesian-reasoningnpx skills add deciqAI/knowledge-skills --skill bayesian-reasoninggit clone --depth 1 https://github.com/deciqAI/knowledge-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/deciqai/knowledge-skills/bayesian-reasoning)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/bayesian-reasoning"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/bayesian-reasoning.svg" alt="Measured on agentmods" 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 | $0.00145 | $0.01989 |
| Opus 5 | $0.00072 | $0.00994 |
| Sonnet 5 | $0.00029 | $0.00398 |
| Haiku 4.5 | $0.00015 | $0.00199 |
Grade A, and why
bayesian-reasoning 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 5d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bayesian Reasoning
Overview
Bayes' theorem: Posterior odds = Prior odds × Likelihood ratio. The strength of belief after evidence equals the strength before, multiplied by how diagnostic the evidence is.
This skill applies Bayesian discipline where people reason about probabilities informally — and failures follow predictable patterns: ignoring the base rate (prior), confusing P(E|H) with P(H|E) (prosecutor's fallacy), over-updating on vivid confirming evidence, treating correlated evidence as independent.
Composes with probabilistic-thinking (Bayes is the operational engine), critical-thinking (formalizes considering alternatives), logical-fallacies (prosecutor's fallacy and base-rate neglect), and first-principles (the prior is bedrock).
When to Use
- High-stakes decision rests on interpreting evidence (medical test, security alert, fraud flag, hiring signal, A/B result)
- "Evidence is consistent with X" is being treated as proof of X
- Base rates ignored — a rare event treated as probable because evidence "looks like" it
- Correlated evidence pieces treated as independent updates
- A benchmark score, AI-capability claim, AI-adoption stat, or AI-capex/valuation figure is being treated as proof without asking how often that signal appears when the underlying claim is false
- Someone says "Bayesian," "prior," "posterior," "base rate," "likelihood ratio," "update"
Not when: genuinely deterministic; no data to anchor a prior; cost of formal update exceeds the value of being more right.
Coaching Novices (Adaptive Front Door)
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output that step's question and nothing more.
- One-line: before believing what the evidence says, ask how common this situation is to start with (prior) and how often evidence would look this way even if the hypothesis is wrong.
- Check fit. Deterministic problems / no prior anchor → not this lens.
- Elicit the real claim and the evidence. What exactly are you deciding, and what evidence do you have?
What ships with it
4 files 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.
- 5d ago First seen · 125 lines · 145 tokens per session scan A 031a1e1a4f90
bayesian-reasoning is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 3d ago), licensed MIT. It adds 145 tokens to every session and 1,989 once invoked, about $0.0007 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
voice-builder
Ingests 5–20 of the user's writing samples and distils a reusable voice-profile.md — signature phrases, sentence-length distribution, opener/closer habits, punctuation quirks, vocabulary do/don't lists, tone sliders, and three calibration paragraphs with self-checks. Other skills load this file so every post sounds…
english-swe-daily
Daily English expression coach for intermediate software engineers. Use this skill whenever the user wants to improve their spoken or written English in a software engineering work context — especially for standups, Slack messages, 1:1s, meetings, giving feedback on code, asking for help, disagreeing politely, or…
agent-teacher
Teach a concept through a runnable code example plus a structured walkthrough, instead of a wall of definitions. Trigger whenever the user wants to understand a technical concept — phrases like "解释一下 X / X 是什么 / 教我 X / X 怎么工作 / 这个 X 是啥 / 我不太懂 X", or "explain X / what is X / teach me X / how does X work / help me…
lecture-notes
Transform raw lecture content (transcript, plain text, or slides) into clean, structured, study-ready notes in Markdown. Use this skill whenever the user pastes lecture material — a transcript (with or without timestamps), course/lecture text, or slide content — and asks for notes, a summary, or help studying. Also…
offensive-exploit-dev-course
Full exploit development course roadmap and syllabus: weekly topics, recommended reading, lab setup, and learning path from vulnerability classes through advanced exploitation. Use to structure exploit dev training or onboard new researchers.
master-debate
Use when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争. Differs from /compare-masters (parallel single-round) by being adversarial multi-round via fresh-subagent orchestration. Topics 空有 / 禅净 / 性相 / 戒律 vs 内观 — trigger is adversarial framing…