council

Plugin council in rube-de/claude-council. Commands read from the repo's manifest — 1 month ago.

Skills (2)

• council-reference

  Council review reference data — expertise weights, structured response format, scoring thresholds, and false positive taxonomy. Background knowledge for council subagents.

• council

  Consult external AI council (Gemini, Codex, Qwen, GLM-4.7) for thorough reviews and consensus-driven decisions. Use ONLY when explicitly invoked with "/council" or when user says "consult the council", "invoke council", or "council review". Do NOT auto-trigger on generic phrases like "thorough revie

Subagents (11)

• claude-bugs

  Internal Claude subagent for bug detection in code review. Has native codebase access to follow call chains, check type definitions, verify edge cases, and trace error propagation. Launched automatically by council review workflows — not invoked directly by users.

• claude-compliance

  Internal Claude subagent for CLAUDE.md and code comment compliance checking. Reads the project's CLAUDE.md files directly and compares changes against stated rules. Launched automatically by council review workflows — not invoked directly by users.

• claude-history

  Internal Claude subagent for historical context analysis in code review. Uses git blame, commit history, and previous change patterns to identify regressions and recurring issues. Launched automatically by council review workflows — not invoked directly by users.

• claude-quality

  Internal Claude subagent for code quality analysis in code review. Checks readability, complexity, duplication, and pattern consistency by comparing against the broader codebase. Launched automatically by council review workflows — not invoked directly by users.

• claude-security

  Internal Claude subagent for security-focused code review. Has native codebase access (Read, Grep, Glob, Bash) to follow imports, check auth flows, trace input paths, and verify sanitization. Launched automatically by council review workflows — not invoked directly by users.

• codex-consultant

  Use this agent when the user asks for code review, plan review, solution debates, architecture decisions, or wants a second opinion from an external perspective. This agent should be used proactively whenever significant code is written, implementation plans are proposed, or when weighing multiple a

• gemini-consultant

  Use this agent when you need external expert feedback on implementation plans, code reviews, architectural decisions, or when debating between multiple solution approaches. This agent should be invoked proactively before implementing non-trivial features, after writing significant code, or when faci

• glm-consultant

  Use this agent when you need external expert feedback from Z.AI's GLM-4.7 model via OpenCode CLI. GLM excels at code review, algorithm analysis, and alternative perspectives on architecture. Use for diverse viewpoints, PR reviews, or when you need a different model's take on a problem.\n\nExamples:\

• kimi-consultant

  Use this agent when you need external expert feedback from Moonshot AI's Kimi K2.5 model via OpenCode CLI. Kimi excels at code analysis, long-context reasoning, algorithm design, and creative problem-solving. Use for diverse viewpoints, PR reviews, or when you need strong coding-focused analysis.\n\

• qwen-consultant

  Use this agent when you need external expert feedback on code quality, refactoring suggestions, detailed explanations, or creative brainstorming. This agent excels at code analysis, performance optimization, and generating novel ideas through structured brainstorming frameworks.\n\nExamples:\n\n<exa

• review-scorer

  Internal scoring agent for council review workflows. Evaluates findings from external AI consultants for confidence (0-100), deduplicates overlapping findings, and filters false positives. Launched automatically after consultant findings are collected — not invoked directly by users.\n\nExamples:\n\

Hooks (1)

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/scripts/preflight.sh

Similar plugins