think-tank-dialectic

think-tank-dialectic is a skill for Claude Code from cookys/autopilot. It costs 219 tokens per session (562 once invoked), scanned B, original, MIT.

A decision method based on thesis, opposing view, and synthesis for choices that are difficult to reverse and have serious trade-offs.

In plain words
What is it for?
It helps examine a high-stakes technical or project decision through competing positions and produce a reasoned conclusion, with limits on how many rounds it uses.
Why use it?
It helps when two options both have strong reasons behind them and ordinary discussion has not produced agreement.

Skill for Claude Code

Written for Claude Code: dynamic context !`command`.

Part of the autopilot plugin — 33 skills, 3 agents, 7 hooks shipped together

Good fit It helps examine a high-stakes technical or project decision through competing positions and produce a reasoned conclusion, with limits on how many rounds it uses.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cookys/autopilot/think-tank-dialectic
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 cookys/autopilot --skill think-tank-dialectic
Clone the repo
git clone --depth 1 https://github.com/cookys/autopilot

Made for: Claude Code.

Or install autopilot, the plugin that ships this one along with the rest of its 33 skills, 3 agents, 7 hooks.

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 think-tank-dialectic

README.md
[![agentmods](https://agentmods.dev/badge/skills/cookys/autopilot/think-tank-dialectic/github.svg)](https://agentmods.dev/skills/cookys/autopilot/think-tank-dialectic)
Your own site
<a href="https://agentmods.dev/skills/cookys/autopilot/think-tank-dialectic"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/think-tank-dialectic/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.

agentmods 80×15 button for think-tank-dialectic

Your own site · 80×15
<a href="https://agentmods.dev/skills/cookys/autopilot/think-tank-dialectic"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/think-tank-dialectic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 219 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 562 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00219 $0.00562
Opus 5 $0.00110 $0.00281
Sonnet 5 $0.00044 $0.00112
Haiku 4.5 $0.00022 $0.00056

Measured 9d ago against content hash afe778d587d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

think-tank-dialectic scanned grade B with 1 finding 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 9d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat .claude/dispatch-config.md 2>/dev/null || true`
platforms/codex/plugin/skills/think-tank-dialectic/SKILL.md · 37 lines

What it actually says

Think Tank Dialectic — Hegelian Deliberation

Dispatch Chains (auto-injected)

!cat .claude/dispatch-config.md 2>/dev/null || true

A DIFFERENT tool than think-tank, not an upgrade: resolves genuine stalemates via Thesis → Antithesis → Synthesis. Cost is high; use is rare by design.

Hard rules (the non-negotiables):

  • Never first-resort: reach for autopilot:think-tank first; escalate ONLY when its Decision Brief shows LOW consensus AND the decision is costly to reverse. Do not skip think-tank for a fresh question.
  • Max 2 rounds (there is no R3); session re-entry ladder (2nd invocation on the same confirmed problem = Quick Synthesis, 3rd = refuse with the four-option exit).
  • HIGH R1 consensus (≥5/6) auto-downgrades — no forced dialectic on an aligned panel.
  • Synthesis is NOT a compromise; if no honest higher-order integration exists, the brief says so instead of faking one.

MUST-READ: ../think-tank/references/dialectic-mode.md — the FULL execution protocol (grounding rules 1–5, role composition + drift mitigation, STEP 0–8, brief/scorecard templates). Do not run the dialectic from this summary alone.

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. 9d ago First seen · 37 lines · 219 tokens per session scan B afe778d587d0

Subscribe to this mod's changes

think-tank-dialectic is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed yesterday), licensed MIT. It adds 219 tokens to every session and 562 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens