Council of High Intelligence skill
A skill that convenes a council of thinker personas and runs a structured deliberation on a hard decision, ending with a verdict
- 4,841 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill orchestrates deliberation and model calls and does not write to external systems
- A full panel over several rounds spends more tokens
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/council-of-high-intelligenceDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill orchestrates deliberation and model calls and does not write to external systems
- A full panel over several rounds spends more tokens
This is third-party code. Review the repository files before installing.
What it does
The skill turns the agent into a council coordinator: it picks members from a set of thinker personas, runs them through rounds of analysis, cross-examination and positions, then synthesizes a single verdict. There are modes for a full 18-member panel, predefined topic triads, manual selection, plus quick and duo formats. Configuration can map roles onto different models and providers. Personas and protocols live in separate files, so the panel and the debate rules can be adjusted.
Who it is for. For people making hard architecture, product and strategy decisions who want them examined from multiple angles.
Good fit when
- You need to weigh a contentious decision from several viewpoints
- You want a structured debate instead of one agent opinion
- The decision is costly and you want to see counterarguments
Not a fit when
- You need a fast single answer to a simple question
- You do not want to spend extra tokens on many personas and rounds
Example request
Convene the council and debate whether we should move from a monolith to microservicesLimitations
The council debates the reasoning and clashes positions, but does not verify facts for you. A full panel over several rounds spends noticeably more tokens, and mapping roles to different providers needs their keys.
How to disable. Remove the council plugin via /plugin marketplace remove, or delete the skill folder from the agent's skills directory.
FAQ
Can I choose the exact panel?
Yes, flags set the full panel, a topic triad or a manual member list, plus quick and duo modes.
Do I need multiple providers?
No. By default the council runs on one model; mapping roles to different providers is an optional YAML setup.
Discussion
No questions or reviews yet.
Related
SkillsA parallel divergent ideation skill for agents: fans out under cognitive frames, prunes traps and deepens the best branches
Orchestration layer for Claude Code, Cursor and Codex: a board of 495 expert personas gives a verdict with named dissent, plus hundreds of skills
A skill plus hooks that keep a coding agent on task and cut speculative defenses, unread checksums and scope creep
An inference-time reasoning control skill: deep analysis, long tasks, verification and recovery grounded in durable evidence
A skill that turns several Claude Code, Codex and Cursor windows into a team with a coordinator, shared registry and cross-review
A Claude Code skill that runs multi-agent work by a naval metaphor: planning, parallel tasks with checkpoints, stand-down
README in short
The README covers install as a Claude Code plugin and via install.sh for Codex, Gemini CLI and OpenCode with per-host flags. The command stays /council everywhere. It documents mode and panel flags, panel profiles, model auto-routing and overrides through a project .council.yaml file. There is an installer reference section and a dry run that prints the routing without executing. MIT licensed.
README badge
Original SKILL.md
--- name: council description: "Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems." --- # /council — Council of High Intelligence You are the Council Coordinator. Your job is to convene the right council members, run a structured deliberation, enforce protocols, and synthesize a verdict. Follow the execution sequence below step-by-step. ## Invocation ``` /council [problem] /council --triad architecture Should we use a monorepo or polyrepo? /council --full What is the right pricing strategy for our SaaS product? /council --members socrates,feynman,ada Is our caching strategy correct? /council --profile exploration-orthogonal Should we enter this market now? /council --profile execution-lean --triad ship-now Should we ship today? /council --quick Should we add caching here? /council --duo Should we use microservices or monolith? /council --duo --members torvalds,ada Is this abstraction worth it? /council --models configs/provider-model-slots.example.yaml --full Evaluate our roadmap ``` ## Flags | Flag | Effect | |------|--------| | `--full` | All 18 members | | `--triad [domain]` | Predefined 3-member combination | | `--members name1,name2,...` | Manual selection (2-11) | | `--profile [name]` | Panel profile: `classic`, `exploration-orthogonal`, `execution-lean` | | `--quick` | Fast 2-round mode (200-word analysis → 75-word position, no cross-examination) | | `--duo` | 2-member dialectic using polarity pairs | | `--models [path]` | Manual provider/model slot mapping (overrides auto-routing) | | `--no-auto-route` | Disable auto-routing; use agent frontmatter defaults (Claude-only) | | `--dry-route` | Print the routing table without running the council | | `--chairman [name]` | Override the Chairman who synthesizes the verdict (e.g. `gemini`, `opus`, `gpt-5.4`). Defaults to highest-tier non-panel provider — see STEP 1.6. | Flag priority: `--quick` / `--duo` set the mode. `--full` / `--triad` / `--members` / `--profile` set the panel. `--models` overrides auto-routing. `--no-auto-route`, `--dry-route`, and `--chairman` are additive. ## Project Overrides (`./.council.yaml`)