critical-thinking

critical-thinking is a skill for Claude Code, Codex from deciqAI/knowledge-skills. It costs 115 tokens per session (2,207 once invoked), scanned A, original, MIT.

A method for evaluating a difficult claim by comparing possible explanations and checking each one against the available evidence.

In plain words
What is it for?
It helps challenge assumptions, build competing explanations, find disconfirming evidence, and assess claims about products, technology, research, or strategy.
Why use it?
It helps prevent premature agreement when the same facts could support different interpretations or when a decision has serious consequences.

Skill for Claude CodeCodex

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

Good fit It helps challenge assumptions, build competing explanations, find disconfirming evidence, and assess claims about products, technology, research, or strategy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deciqai/knowledge-skills/critical-thinking
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 deciqAI/knowledge-skills --skill critical-thinking
Clone the repo
git clone --depth 1 https://github.com/deciqAI/knowledge-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 critical-thinking

README.md
[![agentmods](https://agentmods.dev/badge/skills/deciqai/knowledge-skills/critical-thinking.svg)](https://agentmods.dev/skills/deciqai/knowledge-skills/critical-thinking)
Your own site
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/critical-thinking"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/critical-thinking.svg" alt="Measured on agentmods" height="20"></a>
Per session 115 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,207 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 101
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00115 $0.02207
Opus 5 $0.00057 $0.01104
Sonnet 5 $0.00023 $0.00441
Haiku 4.5 $0.00012 $0.00221

Measured 7d ago against content hash 54dfeff00e1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

critical-thinking 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 7d 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.

critical-thinking/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Critical Thinking

Overview

Critical thinking evaluates a conclusion by explicitly testing it against alternative interpretations — the conclusion that survives the most disconfirmation attempts is the one to act on, not the one with the most confirming examples. Operationalized by Richards J. Heuer Jr. (CIA, 1999) as Analysis of Competing Hypotheses (ACH): a matrix marking each evidence-hypothesis pair as Consistent / Inconsistent / N/A. The hypothesis with the fewest Inconsistencies wins.

Compose: first-principles (surface assumptions) · probabilistic-thinking (calibrate evidence) · inversion (generate alternatives). Critical thinking = evaluation; first-principles = construction; occams = selection; second-order = projection.

When to Use

  • High-stakes claim (yours or someone else's) that needs evaluation
  • Multiple interpretations of the same evidence are possible
  • Motivated reasoning detected — conclusion shaped by what you want to be true
  • Team converging on a hypothesis too fast without seriously considering alternatives
  • Evaluating an AI capability or AI-hype claim (e.g. "this benchmark proves the model reasons") where the same evidence fits several explanations (contamination, cherry-picking, teaching-to-the-eval)

When NOT to use: trivial/already-validated claim; only one hypothesis imaginable (use first-principles first); time pressure makes 90-min ACH impossible; values question not a facts question.

Coaching Novices (Adaptive Front Door)

  • Engine mode: user has a concrete claim + evidence → run The Process directly.
  • Coach mode: user is unfamiliar or has no concrete case → guide step by step. In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
  1. One-line what-it-is: critical thinking is testing your conclusion against alternative explanations, looking for the one with the fewest unresolved contradictions — not the most confirming examples.
  2. Check fit against When to Use / When NOT to use. Redirect if trivial or values-only.
  3. Elicit the specific claim under evaluation — "I want to evaluate my thinking" is too vague; need a specific claim. > [WAIT — do not advance until user responds]
  4. Walk through ACH steps one at a time with their input: list hypotheses → list evidence → score matrix → identify survivor. > [WAIT — do not advance until user responds]
  5. Close by naming the most-diagnostic evidence they discovered — the piece that most differentiates hypotheses. > [WAIT — do not advance until user responds]

Read the full file on GitHub · 124 lines

Files

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.

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. 7d ago First seen · 124 lines · 115 tokens per session scan A 54dfeff00e1b

Subscribe to this mod's changes

critical-thinking is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 115 tokens to every session and 2,207 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 2026-08-31.

Related

Other skills, from other repositories