dialectic

A structured debate process in which two helper agents defend opposing positions while another analyzes their disagreement and forms a synthesis.

In plain words
What is it for?
Use it to explore difficult questions through opposing arguments, structural analysis, and a conclusion that reframes the original issue.
Why use it?
It helps examine contradictions without requiring the user to personally commit to either side.

Skill for Claude CodeCodex

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 skills/abilityai/cornelius/dialectic
Any agent
npx skills add Abilityai/cornelius --skill dialectic
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

Made for: Claude Code, Codex.

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 22,760 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00122 $0.22760
Opus 5 $0.00061 $0.11380
Sonnet 5 $0.00024 $0.04552
Haiku 4.5 $0.00012 $0.02276

Measured 2d ago against content hash 6c0f239ee2b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dialectic 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 2d 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/skills/dialectic/SKILL.md · 1,144 lines

How it starts

The opening of the file, as written. The whole thing — 1,144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The Electric Monks — Dialectic Skill

An artificial belief system for building deeper understanding through productive contradiction.

Two subagent sessions — the Electric Monks — believe fully committed positions so you don't have to. A third (the orchestrator) performs structural analysis of their contradiction and generates a synthesis (Aufhebung) that transforms the question itself. The user orchestrates from a belief-free position, freed from the cognitive load of holding either position.

Why this works: The bottleneck in human reasoning isn't intelligence — it's belief. Once you believe a position, you can't simultaneously hold its negation at full strength. You hedge, you steelman weakly, you unconsciously bias the comparison. The Electric Monks carry the belief load at full conviction, which frees you to operate in the space above belief — analyzing the structure of the contradiction rather than being inside either side. In Boyd's terms: outsourcing belief work leads to faster transients. Each dialectical cycle is a reorientation that would take weeks of natural thinking, compressed into minutes because you carry zero belief inertia.

When to Use This Skill

Use when:

  • The user wants to stress-test an idea against the strongest possible counter-argument
  • The user is torn between two positions and the tension feels genuine, not just a preference
  • A decision has real stakes and the tradeoffs are unclear
  • The user wants to build a deeper mental model of a domain, not just pick an answer
  • The problem space is poorly understood and needs exploration from multiple angles
  • Requirements genuinely conflict and can't be resolved by simple tradeoff analysis

Do NOT use when:

  • The question is purely empirical (just look up the answer)
  • One side is obviously correct and doesn't need dialectical treatment
  • The user wants a quick recommendation, not deep analysis

<core_concepts>

Core Concepts (Read This First)

Three frameworks drive every phase of this skill. Internalize them before proceeding — they determine how you execute, not just why.

Read the full file on GitHub · 1,144 lines

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. 2d ago First seen · 1,144 lines · 122 tokens per session scan A 6c0f239ee2b9

Subscribe to this mod's changes

dialectic is a skill published in the GitHub repository Abilityai/cornelius (104 stars, last pushed 9d ago), licensed MIT. It adds 122 tokens to every session and 22,760 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 2026-08-30.