Most council skills give you opinions. DecisionCouncil gives you a ranked verdict, checked claims, and the dissent you would have missed.
One install. Lite mode by default (~4 sub-agents). Scout pulls recent signal via last30days. Fact Checker verifies numbers via deep-research. You get #1 marked, strongest counterargument preserved, and the one condition that would flip the call.
Works in Cursor and Claude Code.
npx skills add Endokelp/DecisionCouncil --skill council -g -yThat installs the council skill globally. For companion research skills in one shot:
Windows (PowerShell):
git clone https://github.com/Endokelp/DecisionCouncil.git $env:TEMP\DecisionCouncil
& "$env:TEMP\DecisionCouncil\install.ps1"macOS / Linux:
git clone https://github.com/Endokelp/DecisionCouncil.git /tmp/DecisionCouncil
/tmp/DecisionCouncil/install.shRestart your editor after install.
The skill only runs when you name it (disable-model-invocation: true). Say one of:
| You type | Mode |
|---|---|
council this: Mac Studio vs DGX Spark under $5k |
Lite (default) |
/council Which vendor for a 3-year lock-in? |
Lite |
/council full Should we pivot pricing? |
Full (~2 to 3x tokens) |
pressure-test this, war room this, debate this |
Lite |
Good questions: vendor lock-in, hardware purchases, architecture forks, strategy pivots, anything expensive to get wrong.
Skip it: trivia, cheap reversible choices, pure writing tasks, code review (use a reviewer skill instead).
## Council: Local AI brain under $5k
1. **Mac Studio M4 Max 128GB** (WINNER)
Trade-off: swap-on-demand for 70B, not resident dual-30B parallel.
2. DGX Spark 128GB
Trade-off: dense 70B decode ~5 tok/s; thermal reports still messy.
3. Dual used RTX 3090 build
Trade-off: best tok/s per dollar, wrong for a quiet 24/7 desk box.
**Strongest dissent:** Skeptic argues Spark CUDA ecosystem wins if fine-tuning becomes primary, not 20% side work.
**Condition that would change the answer:** verified firmware lifts Spark dense-70B above ~15 tok/s AND fixes sustained thermal shutdowns.The market already has councils. They solve different problems.
| affaan-m/council | karpathy/llm-council | aiwithremy/llm-council | DecisionCouncil | |
|---|---|---|---|---|
| What it is | Opinion council inside a 200K+ star skill pack | Multi-model web app | 5-advisor Claude skill | Standalone evidence council |
| Research | You bring context | None built-in | None built-in | last30days Scout + deep-research Fact Checker |
| Output | Compact verdict + dissent line | Chairman synthesis | Chairman + peer review | Ranked list, #1 marked + falsifier |
| Token model | 3 sub-agents, one round | Full pipeline always | 5 advisors + review | Lite default, Full optional |
| Cursor | Claude Code ecosystem | N/A (separate app) | Claude-focused | Cursor Task + Claude Code |
| Best for | Ambiguous tradeoffs, fast | Compare models side by side | Business/creator decisions | High-stakes, evidence-bound forks |
affaan-m ships council inside everything-claude-code. That is smart distribution: one mega repo, 3.7K+ installs on skills.sh, four voices (Skeptic, Pragmatist, Critic) with clean anti-anchoring. It is built for decision-making under ambiguity, not for verifying whether a benchmark number is real.
DecisionCouncil is the council you run when the decision has a price tag. Scout establishes a shared baseline once (so five agents do not re-google the same spec sheet). Advocate and Skeptic argue from different angles. Fact Checker runs claims through deep-research Quick mode. You leave with a ranked shortlist, not just a vibes-based recommendation.
Karpathy's council compares models. aiwithremy's council convenes five advisors. affaan-m's council surfaces tradeoffs fast inside ECC. DecisionCouncil is the evidence-bound council for Cursor and Claude Code.
Install lands at ~/.cursor/skills/council/. Invoke with council this: or /council.
Sub-agents use the Task tool (generalPurpose, run_in_background: false). Spawn Scout, then Advocate + Skeptic in parallel, then Fact Checker. Chairman synthesis stays in the main session.
Details: skills/council/SKILL.md
Also installs to ~/.claude/skills/council/. Use /council or /council full.
DecisionCouncil/
├── AGENTS.md
├── skills/council/SKILL.md
├── install.ps1
├── install.sh
└── README.md
- Methodology: Andrej Karpathy, LLM Council
- ECC council pattern: affaan-m/everything-claude-code
- Community skill: aiwithremy/claude-skills-llm-council
- Research companions: last30days, deep-research
- Built by Endokelp. Dogfooded on a real hardware council (JARVIS brain selection, 2026-06).
MIT. See LICENSE.