agents-consilium

Solid

Query external AI agents (Codex, Claude Code, OpenCode, native Grok Build, Gemini) for independent second opinions, multi-depth code review, repository context exploration, and full-YOLO single-agent delegation. Three public modes via scripts/consilium: review (read-only ask/code), explore (read-only exploration of a local or remote repository — clones remotes, answers from cited evidence, Grok 4.5 by default), and delegate (exact agent, no sandbox; optional --steerable long session with steer/status/cancel, plus --detach to outlive the caller and wait/watch/list to block on, follow, or rediscover a run). Use for architecture choices, security review, deep multi-stage review, understanding an unfamiliar or third-party codebase, handing a whole task to one agent, or waiting on a delegated agent that was started earlier. Not for simple questions answerable from docs or the codebase.

AI & Automation 135 stars 10 forks Updated today MIT

Install

View on GitHub

Quality Score: 87/100

Stars 20%
71
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Consilium v6: Multi-Agent Review, Exploration & Delegation Query external AI agents for independent expert opinions, structured code review, repository exploration, or full-YOLO task delegation. Review and explore stay read-only. Delegate hands the whole task to **exactly one** explicitly selected agent in the caller's CWD. ## Public CLI (only entrypoint) ```bash scripts/consilium review ask [...] scripts/consilium review code --depth basic|specialists|super|ultra [...] scripts/consilium explore [--repo SOURCE] [--ref REF] [...] scripts/consilium delegate -a <exact-agent-id> [...] scripts/consilium delegate -a <exact-agent-id> --steerable [...] scripts/consilium delegate -a <exact-agent-id> --detach [...] scripts/consilium delegate steer RUN_ID [--mode auto|queue|interrupt] [...] scripts/consilium delegate status RUN_ID [--json] scripts/consilium delegate cancel RUN_ID scripts/consilium delegate wait RUN_ID [--timeout SEC] [--json] [--quiet] scripts/consilium delegate watch RUN_ID [--timeout SEC] [--heartbeat SEC] [--json] scripts/consilium delegate list [--active|--all] [--reap] [--json] scripts/consilium --list-agents ``` Old public scripts (`consensus-query.sh`, `code-review.sh`, `superreview.sh`, `ultrareview.sh`, `*-query.sh`) were removed in v5. Internal modules live under `scripts/lib/`. ## Why this skill **Different frontier models see different things.** Parallel independent reviews surface issues and alternatives one model alone misses. Consilium keeps agent...

Details

Author
CodeAlive-AI
Repository
CodeAlive-AI/ai-driven-development
Created
7 months ago
Last Updated
today
Language
Python
License
MIT

Integrates with

Bundled in these plugins

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

ai-consultants

Consult Gemini, Codex, Mistral Vibe, Claude, Kimi, Qwen, MiniMax, GLM, Grok, and DeepSeek as external experts for coding questions. Automatically excludes the invoking agent from the panel to avoid self-consultation. Use when you have doubts about implementations, want a second opinion, need to choose between different approaches, or when explicitly requested with phrases like "ask the consultants", "what do the other models think", "compare solutions", "get expert opinions", "I'm not sure about this approach", "what would other models say". Make sure to consult this skill whenever the user is weighing trade-offs, comparing architectures, validating complex solutions, or wants multiple perspectives on any non-trivial coding decision. Do NOT use for simple questions that only need one model's answer or when you already have high confidence in a solution.

7 Updated today
matteoscurati
AI & Automation Listed

multi-agent-repo

Use when auditing or setting up a repository for multi-agent development across Claude Code, Claude Desktop, Cursor, Codex, Gemini CLI, and OpenCode — or making a repo compatible with those assistants. Triggers: multi-agent repo, audit agent setup, AGENTS.md gaps, make compatible with Claude and Cursor, add Codex support, add Gemini CLI support, add OpenCode support, add cursor rules, generate AGENTS.md, capability registry, agent drift, canonical AGENTS.md, multi-agent-repo review/plan/dev, multi-platform AI support.

2 Updated today
Tamircohen28
AI & Automation Listed

consult

Bring in another coding agent as an independent second opinion. Use when the user explicitly asks to ask, consult, cross-check, debate with, or get a second opinion from another agent/model, including named backends such as Gemini, OpenCode, Claude, Codex, Pi, or an added backend. Here Pi means the Pi backend, not the number π or Raspberry Pi hardware; and names like GPT, OpenAI, Sonnet, Opus, or Qwen name a model or provider, not a backend (resolve them to a model on a chosen backend). Also use for clearly high-risk independent review where another model is materially needed for safety, security, architecture, or regression risk. Do not trigger for ordinary review, debugging, or brainstorming unless external-agent help is requested. Treat responses as advice and verify claims locally before acting.

1 Updated yesterday
mikielek