← Back to Skills Marketplace
0xnyk

Council

by 0xNyk · GitHub ↗ · v0.1.0
cross-platform ⚠ suspicious
291
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install council-of-high-intelligence
Description
Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems.
README (SKILL.md)

/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.

Invocation

/council [problem description]
/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?

Flags

  • --full — convene all 11 members
  • --triad [domain] — use a predefined triad (see table below)
  • --members name1,name2,... — manual member selection (2-11 members)
  • No flag with a domain keyword → auto-select the matching triad
  • No flag, no keyword → default to Architecture triad

The 11 Council Members

Agent Figure Domain Model Polarity
council-aristotle Aristotle Categorization & structure opus Classifies everything
council-socrates Socrates Assumption destruction opus Questions everything
council-sun-tzu Sun Tzu Adversarial strategy sonnet Reads terrain & competition
council-ada Ada Lovelace Formal systems & abstraction sonnet What can/can't be mechanized
council-aurelius Marcus Aurelius Resilience & moral clarity opus Control vs acceptance
council-machiavelli Machiavelli Power dynamics & realpolitik sonnet How actors actually behave
council-lao-tzu Lao Tzu Non-action & emergence opus When less is more
council-feynman Feynman First-principles debugging sonnet Refuses unexplained complexity
council-torvalds Linus Torvalds Pragmatic engineering sonnet Ship it or shut up
council-musashi Miyamoto Musashi Strategic timing sonnet The decisive strike
council-watts Alan Watts Perspective & reframing opus Dissolves false problems

Polarity Pairs (Why These 11)

  • Socrates vs Feynman: Both question, but Socrates destroys top-down; Feynman rebuilds bottom-up
  • Aristotle vs Lao Tzu: Aristotle classifies everything; Lao Tzu says structure IS the problem
  • Sun Tzu vs Aurelius: Sun Tzu wins external games; Aurelius governs the internal one
  • Ada vs Machiavelli: Ada abstracts toward formal purity; Machiavelli anchors in messy human incentives
  • Torvalds vs Watts: Torvalds ships concrete solutions; Watts questions whether the problem exists
  • Musashi vs Torvalds: Musashi waits for the perfect moment; Torvalds says ship it now

Pre-defined Triads

Domain Keyword Triad Rationale
architecture Aristotle + Ada + Feynman Classify + formalize + simplicity-test
strategy Sun Tzu + Machiavelli + Aurelius Terrain + incentives + moral grounding
ethics Aurelius + Socrates + Lao Tzu Duty + questioning + natural order
debugging Feynman + Socrates + Ada Bottom-up + assumption testing + formal verification
innovation Ada + Lao Tzu + Aristotle Abstraction + emergence + classification
conflict Socrates + Machiavelli + Aurelius Expose + predict + ground
complexity Lao Tzu + Aristotle + Ada Emergence + categories + formalism
risk Sun Tzu + Aurelius + Feynman Threats + resilience + empirical verification
shipping Torvalds + Musashi + Feynman Pragmatism + timing + first-principles
product Torvalds + Machiavelli + Watts Ship it + incentives + reframing
founder Musashi + Sun Tzu + Torvalds Timing + terrain + engineering reality

Deliberation Protocol

Round 1: Independent Analysis (PARALLEL)

Spawn each selected council member as a subagent using the Agent tool:

  • subagent_type: "general-purpose" (agents are in ~/.claude/agents/)
  • Each member receives the problem statement and produces their standalone analysis
  • Run all members IN PARALLEL for speed
  • Each member follows their own Output Format (Standalone) template

Prompt template for each member:

You are operating as a council member in a structured deliberation.
Read your agent definition at ~/.claude/agents/council-{name}.md and follow it precisely.

The problem under deliberation:
{problem}

Produce your independent analysis using your Output Format (Standalone).
Do NOT try to anticipate what other members will say.
Limit: 400 words maximum.

Round 2: Cross-Examination (SEQUENTIAL)

After collecting all Round 1 analyses, send each member a follow-up:

Here are the other council members' analyses:

{all Round 1 outputs}

Now respond:
1. Which member's position do you most disagree with, and why? (Engage their specific claims)
2. Which member's insight strengthens your own position? How?
3. Has anything changed your view? If so, what specifically?
4. Restate your position in light of this exchange.

Limit: 300 words maximum. You MUST engage at least 2 other members by name.

Run these sequentially so later members can reference earlier cross-examinations.

Round 3: Synthesis

Send each member a final prompt:

Final round. State your position declaratively in 100 words or less.
Socrates: you get exactly ONE question. Make it count. Then state your position.
No new arguments — only crystallization of your stance.

Anti-Recursion Enforcement (Coordinator Duties)

You MUST intervene if:

  • Socrates re-asks a question that another member has directly addressed with evidence → remind of the hemlock rule, force a 50-word position statement
  • Any member restates their Round 1 position without engaging Round 2 challenges → send back with specific challenge they must address
  • Exchange exceeds 2 messages between any member pair → cut off and move to Round 3

Tie-Breaking Rules

  • 2/3 majority → consensus. Record dissenting position in Minority Report.
  • No majority → present the dilemma to the user with each position clearly stated. Do NOT force consensus.
  • Domain expert weight: The member whose domain most directly matches the problem gets 1.5x weight. (e.g., Ada for formal systems problems, Sun Tzu for competitive strategy)

Output: Council Verdict

After all 3 rounds, synthesize the following deliverable:

## Council Verdict

### Problem
{Original problem statement}

### Council Composition
{Members convened and why}

### Consensus Position
{The position that survived deliberation — or "No consensus reached" with explanation}

### Key Insights by Member
- **{Name}**: {Their most valuable contribution in 1-2 sentences}
- ...

### Points of Agreement
{What all/most members converged on}

### Points of Disagreement
{Where positions remained irreconcilable}

### Minority Report
{Dissenting positions and their strongest arguments}

### Unresolved Questions
{Questions the council could not answer — inputs needed from user}

### Recommended Next Steps
{Concrete actions, ordered by priority}

Example Usage

User: /council --triad strategy Should we open-source our agent framework?

Coordinator:

  1. Identifies triad: Sun Tzu + Machiavelli + Aurelius
  2. Spawns 3 agents in parallel for Round 1
  3. Collects analyses, runs Round 2 sequentially
  4. Collects Round 3 final statements
  5. Synthesizes Council Verdict with consensus/dissent/next steps
Usage Guidance
This skill appears to implement what it claims (a multi‑persona deliberation council), but it grants each persona powerful tools (shell access, file read/glob, and web fetch/search) that are not explicitly limited by the SKILL.md. Before installing: 1) Inspect install.sh and do not run it until you confirm it only copies files into ~/.claude and does nothing unexpected. 2) Review each agents/council-*.md file: the 'tools' lines (Bash, Read, Glob, WebFetch, WebSearch) are the key risk — consider removing or restricting Bash/Read/Glob if you don't want subagents to access local files. 3) If possible, run the skill in a sandboxed account or VM where it cannot access sensitive files or credentials. 4) If you must install to your main environment, consider editing the agent files to remove network (WebFetch) or shell (Bash) tools so they can only reason over the included persona definitions. 5) Watch for any unexpected outbound network activity while running the skill. If you want, I can (a) list exact lines to search for in install.sh, (b) point out where to remove or alter 'tools' entries in the persona files, or (c) help craft a safer, restricted SKILL.md variant.
Capability Analysis
Type: OpenClaw Skill Name: council-of-high-intelligence Version: 0.1.0 The 'Council of High Intelligence' skill bundle is a sophisticated multi-agent deliberation framework designed to provide diverse perspectives on complex problems. The installation script (install.sh) follows standard practices for deploying agents and skills to the ~/.claude directory without any suspicious network calls or persistence mechanisms. The instructions in SKILL.md and the various agent persona files (e.g., council-socrates.md, council-torvalds.md) are well-defined, focusing entirely on the structured deliberation protocol and analytical methods, with no evidence of malicious prompt injection, data exfiltration, or unauthorized tool usage.
Capability Assessment
Purpose & Capability
The name/description (a multi-persona 'council') match the included SKILL.md and the 11 persona files. Having subagents for different personas is consistent with the stated goal. However, every persona file declares tools like Read, Grep, Glob, Bash, WebSearch, and WebFetch — capabilities that go beyond pure in-memory reasoning. Those tools are plausible for personas that cite 'read' or 'search' behavior, but they are broader than a minimal deliberation skill (they allow arbitrary file reads and shell commands). This is not necessarily malicious, but it is more privilege than the description implies.
Instruction Scope
Runtime instructions explicitly tell the coordinator to spawn subagents and to have each member 'Read your agent definition at ~/.claude/agents/council-{name}.md'. The protocol otherwise leaves subagents free to use their declared tools in Round 1–3. The SKILL.md does not restrict those tools' use to only the agent files, so subagents could (through Bash/Read/Grep/Glob) access arbitrary filesystem paths and (through WebFetch/WebSearch) external network resources. The instructions therefore permit actions that could expose local files or transmit data externally, which is scope creep relative to a simple deliberation assistant.
Install Mechanism
No install spec from an external URL is present; installation is instruction-only plus an included install.sh and copy instructions. The README instructs copying agents into ~/.claude/agents/ and SKILL.md into ~/.claude/skills/. That is a normal, low-risk install pattern for a local agent skill. The actual install.sh content was not provided for review here; if it performs only the copy operations shown in README, risk is low. If it runs other commands, that would need review.
Credentials
The skill declares no required env vars or credentials, which matches its purpose. However, the persona files grant tools (Bash, Read, Glob, WebFetch) that can be used to read environment variables or local credentials from disk at runtime even though none are requested. Because the SKILL.md does not constrain the tools' use, the effective permissions are larger than declared — a proportionality mismatch that increases exposure of secrets on the host.
Persistence & Privilege
The skill is not 'always: true' and is user-invocable only, which is reasonable. Installation copies files into ~/.claude/agents and ~/.claude/skills — this creates a persistent presence in the user's Claude environment (normal for local skills). There is an install.sh included; its actions should be inspected before running. The skill does not declare modifying other skills or global config, but the copy into ~/.claude is a local persistent change.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install council-of-high-intelligence
  3. After installation, invoke the skill by name or use /council-of-high-intelligence
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Initial release of council-of-high-intelligence skill. - Convene multi-persona "Council of High Intelligence" for complex problem analysis. - Includes 11 historical thinker personas, each with unique analytical styles and domains. - Supports invocation by domain triad, full council, or custom member list. - Three-round deliberation protocol: Independent Analysis, Cross-Examination, Synthesis. - Coordinator enforces protocols, manages anti-recursion, and synthesizes a Council Verdict summary with consensus, dissent, and actionable next steps.
Metadata
Slug council-of-high-intelligence
Version 0.1.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Council?

Convene the Council of High Intelligence — multi-persona deliberation with historical thinkers for deeper analysis of complex problems. It is an AI Agent Skill for Claude Code / OpenClaw, with 291 downloads so far.

How do I install Council?

Run "/install council-of-high-intelligence" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Council free?

Yes, Council is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Council support?

Council is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Council?

It is built and maintained by 0xNyk (@0xnyk); the current version is v0.1.0.

💬 Comments