philo-council

philo-council is a skill for Claude Code, Codex from umair-tareen/philosopher-council. It costs 108 tokens per session (752 once invoked), scanned A, original, MIT.

A skill that asks a council of named philosophers to examine a question, decision, plan, or claim. It presents each viewpoint, virtue scores, a synthesis, and a minority report showing the strongest disagreement.

In plain words
What is it for?
Use it to deliberate decisions, test claims, examine unclear terms, compare positions on a yes-or-no proposition, or make forecasts.
Why use it?
It makes competing lines of reasoning visible instead of reducing a difficult question to one unexplained answer.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to deliberate decisions, test claims, examine unclear terms, compare positions on a yes-or-no proposition, or make forecasts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/umair-tareen/philosopher-council/philo-council
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 umair-tareen/philosopher-council --skill philo-council
Clone the repo
git clone --depth 1 https://github.com/umair-tareen/philosopher-council

Made for: Claude Code, Codex.

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 philo-council

README.md
[![agentmods](https://agentmods.dev/badge/skills/umair-tareen/philosopher-council/philo-council/github.svg)](https://agentmods.dev/skills/umair-tareen/philosopher-council/philo-council)
Your own site
<a href="https://agentmods.dev/skills/umair-tareen/philosopher-council/philo-council"><img src="https://agentmods.dev/badge/skills/umair-tareen/philosopher-council/philo-council/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 philo-council

Your own site · 80×15
<a href="https://agentmods.dev/skills/umair-tareen/philosopher-council/philo-council"><img src="https://agentmods.dev/badge/skills/umair-tareen/philosopher-council/philo-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 752 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00108 $0.00752
Opus 5 $0.00054 $0.00376
Sonnet 5 $0.00022 $0.00150
Haiku 4.5 $0.00011 $0.00075

Measured 11d ago against content hash 6a69479172ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

philo-council 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 11d 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.

skills/philo-council/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

philo-council: convene the philosopher council

Put the user's question to the philosopher council and present the deliberation: each seat evaluates through its own documented methodology with virtue scores (Wisdom, Courage, Justice, Temperance), Ibn ʿArabī synthesizes, and the strongest dissent survives as a minority report. The value is legible disagreement, not a single oracle answer.

How to run it

Preferred - MCP tools. If the philo-council MCP server is connected (tools named like mcp__philo-council__deliberate):

  1. Optionally call precedents first with the question - it is free (no LLM calls) and shows whether the bench has already ruled on something similar.
  2. Call deliberate with:
    • question (required) - phrase it as a single deliberable question
    • context - background the bench should know
    • fullCouncil: true - all ten deliberators instead of the quorum of four (use only when the user asks for the full bench; it is ~2.5x the cost)
    • mode - socratic (fuzzy terms need examining), oxford (binary proposition), delphi (forecast), else omit for open deliberation

Fallback - CLI. If the MCP server is not connected but the philosopher-council repo is available locally:

pnpm --dir <path-to-philosopher-council> ask "the question"
pnpm --dir <path-to-philosopher-council> ask --full-council --mode oxford "..."

Requires pnpm install once, plus an API key in .env (ANTHROPIC_API_KEY, or any seat remapped to openai/gemini/ollama via COUNCIL_MODELS). DRY_RUN=1 gives an instant offline demo with mock opinions.

If neither is available, say so and point the user at https://github.com/umair-tareen/philosopher-council - do not fake a deliberation by role-playing the philosophers yourself.

Presenting the result

  • Lead with the council's direct answer, then the verdict score and recommendation (amplify / track / ignore).
  • Always surface the minority report - the dissent is the product. Never smooth it into the consensus.
  • Quote at most 2-3 individual opinions inline; the full transcript path is in the output for the rest.
  • Keep the framing honest: these are prompt-engineered lenses on one model family, not eleven independent minds. If the user asks whether the council "beats" a single model, the repo's own published eval says the margin is thin (0.728 vs 0.717) - its value is auditable, multi-perspective reasoning with preserved dissent.

Read the full file on GitHub · 58 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. 11d ago First seen · 58 lines · 108 tokens per session scan A 6a69479172ad

Subscribe to this mod's changes

philo-council is a skill published in the GitHub repository umair-tareen/philosopher-council (5 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 752 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

pydantic-ai

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

davila7/claude-code-templates · 32 tokens

free-llm-apis

Guide users through obtaining and configuring free API keys for LLM providers. Use when the user wants to set up a free LLM API, get a free API key, connect to a free model provider, configure an OpenAI-compatible endpoint at no cost, or asks about free tiers for AI models. Triggers on "free API key", "free LLM", "set…

mnfst/awesome-free-llm-apis · 116 tokens

microservices-expert

Expert-level microservices architecture, patterns, service mesh, and distributed systems. Use when the user mentions distributed systems, service mesh, or architecture, or when the task involves Microservices Principles, Architecture Patterns, Communication, or Data Management.

personamanagmentlayer/pcl · 52 tokens

stockbreeder-expert

Expert-level livestock management, animal health monitoring, breeding programs, and ranch management. Use when the user mentions livestock, animal husbandry, breeding, ranch management, or veterinary, or when the task involves Livestock Management, Animal Health, or Technologies.

personamanagmentlayer/pcl · 56 tokens

ai-architect-expert

Expert-level AI system design, MLOps, architecture patterns, and AI infrastructure. Use when the user mentions AI architecture, MLOps, system design, AI infrastructure, or scalability, or when the task involves AI System Architecture, MLOps Infrastructure, Scalability Patterns, or Architecture Design.

personamanagmentlayer/pcl · 66 tokens

ai-engineer-expert

Expert-level AI implementation, deployment, LLM integration, and production AI systems. Use when the user mentions AI engineering, LLM, deployment, production AI, or integration, or when the task involves LLM Patterns, LLM Integration, or Production Systems.

personamanagmentlayer/pcl · 58 tokens