critical-thinking CLAUDE.md

critical-thinking CLAUDE.md is an instructions file for coding agents from Johna2an/critical-thinking. It costs 301 tokens per session, scanned A, original, MIT.

A set of instructions for Critical Thinking, an agent skill that makes reasoning more explicit by using probabilities, base rates, and ways to disprove a claim.

In plain words
What is it for?
Use it when changing the skill, running its evaluation process, updating documentation, or checking claims against the project's review rules.
Why use it?
It protects the installable skill from accidental edits to frozen evaluation files and requires evidence when behavior changes.

Instructions file

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.

agentmods
npx agentmods add instructions/johna2an/critical-thinking/claude-md
Clone the repo
git clone --depth 1 https://github.com/Johna2an/critical-thinking

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 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/johna2an/critical-thinking/claude-md.svg)](https://agentmods.dev/instructions/johna2an/critical-thinking/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/johna2an/critical-thinking/claude-md"><img src="https://agentmods.dev/badge/instructions/johna2an/critical-thinking/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 301 This file is loaded in full into every session.
When invoked 301 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00301 $0.00301
Opus 5 $0.00151 $0.00151
Sonnet 5 $0.00060 $0.00060
Haiku 4.5 $0.00030 $0.00030

Measured 4d ago against content hash b79bfec269a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critical-thinking CLAUDE.md 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 4d 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.

CLAUDE.md · 12 lines

What it actually says

CLAUDE.md

critical-thinking is an open-source Agent Skill for Claude Code and Claude-based agents that makes Claude reason with explicit probabilities, base rates, and falsifiers: in blind evaluations it ranked first in 18 of 18 judge passes against baseline Claude and GPT-5.5.

Read AGENTS.md for the repo map, install command, eval pipeline, and working conventions. The points below are the ones violated most easily:

  1. The installable skill is skill/ only. versions/v1/ is a frozen snapshot for reproducible A/B evals; never edit it.
  2. Claims about the skill ride on evals. Behavioral changes to skill/ need a before/after run of the relevant round in evals/ (see CONTRIBUTING.md for the loop and evals/README.md for the protocol).
  3. Never commit book text or paste long excerpts anywhere in the repo. Reference files are original prose restating each book's methods; short attributed phrases are the ceiling.
  4. Docs prose is plain and declarative: no em dashes, no "not X, but Y" constructions, every number names its measure. Verbatim judge quotes are exempt.
  5. _verdicts.json is derived data. Recompute from judges/*.json + rotation_map.json via the deterministic aggregators in evals/harness/ rather than editing it.
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. 4d ago First seen · 12 lines · 301 tokens per session scan A b79bfec269a0

Subscribe to this mod's changes

critical-thinking CLAUDE.md is an instructions file published in the GitHub repository Johna2an/critical-thinking (5 stars, last pushed 2mo ago), licensed MIT. It adds 301 tokens to every session, about $0.0015 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 instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens