Error Debugging
Security scan passedTwo debugging subagents and three commands that find the root cause of errors, set up error tracking and run multi-agent code reviews.

Put a hard decision to a council of analytical personas that argue it out and return a verdict with dissent, kill criteria and a next step.
by 0xNyk· AI & agentsUnclaimed · Yours? Claim it
4 images
About
Council of High Intelligence is a community skill by 0xNyk for decisions that deserve more than one line of reasoning. One command, /council, hands your question to a panel of deliberately different analytical personas. Each forms a position on its own first, then they cross-examine each other, declare final stances and synthesize a verdict that keeps unresolved questions and dissent instead of smoothing them into consensus. What you can do with it - Convene the full council on a high-stakes choice, such as pricing, open-sourcing or an irreversible launch - Run a quick panel when breadth matters more than a full adversarial round - Run a duo when one tension defines the decision, such as microservices versus a monolith - Pick a named triad for a domain (strategy, risk, shipping, architecture, AI product, ethics and more) or choose the members yourself How it works - Its eighteen lenses are modeled on thinkers such as Aristotle, Socrates, Feynman, Ada Lovelace, Kahneman, Munger, Taleb and Dieter Rams. The maker describes them as analytical instruments, not impersonations: each has a method, known blind spots and a response format. - Claims are labeled as fact, inference, assumption or unknown, and checks flag premature agreement, repeated claims and missing dissent. - Verdicts lead with what's unresolved, then a recommendation with acceptable compromises, kill criteria and one concrete next step. A split vote is returned as a split. - If Codex, Gemini CLI, Ollama, Cursor or an NVIDIA NIM key is available, it spreads seats across those models so one model family doesn't argue both sides. How to install it - In Claude Code: /plugin marketplace add 0xNyk/council-of-high-intelligence, then /plugin install council@council-of-high-intelligence. - For Codex, Gemini CLI or OpenCode, clone the repo and run its installer with the matching flag. The command is /council everywhere. Good to know - The maker suggests it for decisions with real downside, competing values or incomplete evidence, not for factual lookups or cheap, reversible choices. - It's a community project, MIT-licensed.
Once it’s added
“/council Should we open-source our agent framework?”
“/council --quick Should we add caching here?”
“/council --duo Should we use microservices or a monolith?”
“/council --triad risk What could make this launch irreversible?”
“/council --triad strategy Where is our defensible advantage?”
“/council --full What is the right pricing model?”
Before you add it
Reads only
Your question, constraints and the evidence you give it
Makes changes · your agent can ask first
Each persona's position and cross-examination · A verdict with dissent, kill criteria and one next step
Each with its own page
From people who use it
Step by step
No reviews yet. Used Council of High Intelligence? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add 0xNyk/council-of-high-intelligence /plugin install council@council-of-high-intelligence
Scanned and passed · checked 2 h ago
Plugins people install alongside Council of High Intelligence.
Nothing new reaches your agent until a person has looked at it.
Scanned on every change, and again when our rules improve.
Tell us and a person on the trust team will look at it. Or email [email protected].
Nobody has shared how they use Council of High Intelligence yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.
Plugins people install alongside Council of High Intelligence.
Two debugging subagents and three commands that find the root cause of errors, set up error tracking and run multi-agent code reviews.
ByteDance's local MCP server that lets your agent run any shell command or script on your machine, with your own permissions.
Keeps your agent's plan, findings and progress in markdown files on disk, so long tasks survive /clear, crashes and compaction.