Stats
Actions
Tags
From agentops
Runs multi-judge consensus for high-stakes decisions: architecture forks, one-way doors, scoring options. Fires for cross-validation and trust-gate scenarios using multiple AI models.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentops:councilThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill encodes independent-verdict machinery and now lives with the outer
This skill encodes independent-verdict machinery and now lives with the outer
gate product. Canonical: ~/dev/mt-olympus/.claude/skills/council/SKILL.md —
read and follow that file. This stub preserves fleet routing until the
using-agentops catalog closer updates the registry (skill-prune Lane A,
evidence/skill-prune-recon.md).
Council also fires for the use-cases of two folded-in skills:
trust-gate.sh, read skill.trust.json (trust_level + trust_score),
and enforce --require-cross so cross-vendor parity gates the verdict.
Canonical body:
~/dev/mt-olympus/.claude/skills/cross-vendor-trust-gate/SKILL.md.When the decision wants a mixed-model / cross-family panel rather than
single-model judges, the duel substrate is /dual-pane-atm — durable
Opus + Codex (+AGY) panes, or its in-session variant (Agent model: override +
codex exec) that /discovery's fanout gate runs. /reverse-engineer
routes one-way-door steal decisions into council.
/council should we swap the policy engine to Cedar? — runs at the canonical
location; this stub forwards. Read
~/dev/mt-olympus/.claude/skills/council/SKILL.md.Multi-judge runs still bind to the shared Claude runtime surface: claude-code-latest-features.md.
npx claudepluginhub boshu2/agentops --plugin agentopsConvenes four advisory voices (Architect, Skeptic, Pragmatist, Critic) to surface tradeoffs and structured disagreement for ambiguous decisions with multiple valid paths.
Dispatches high-stakes decision prompts to multiple LLM providers in parallel via an MCP server and synthesizes responses to surface blind spots missed by single-model review.
Assembles a multi-perspective deliberation committee with adversarial review, external LLM opinions, and community sentiment analysis. Outputs a Tradeoff Map with contention points and step-back insights.