Use when you want a delegated second opinion or implementation from GPT (Codex), Gemini, Grok (xAI), or OpenRouter (config-driven, 400+ models) - seven expert subagents (Architect, Plan Reviewer, Scope Analyst, Code Reviewer, Security Analyst, Researcher, Debugger) and bundled ask-gpt/ask-gemini/ask-grok/ask-openrouter/ask-all/consensus commands, advisory (read-only) or implementation (write; Grok and OpenRouter are advisory-only).
Plugin deliberation from marketplace antonbabenko in antonbabenko/agent-plugins. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
architectSystem design, tradeoffs, and complex technical decisions.
code-reviewerFind bugs, security holes, and maintainability issues in a diff or file.
debuggerRank root-cause hypotheses and propose the smallest safe fix.
deliberationWhen and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
plan-reviewerValidate that a work plan is executable before work starts.
reload-mcpGracefully cycle dashboard and audit MCP processes after deliberation is updated.
researcherResearch external libraries, APIs, and best practices, with evidence.
scope-analystCatch ambiguities and hidden requirements before planning.
security-analystThreat-model and find vulnerabilities, with practical remediation.
writing-editorEdit prose so it reads like its author wrote it, keeping every fact and the author's voice.
/deliberation:analyzeAnalyze recent runs - per-model latency, tokens, and verdict agreement - and suggest model/reasoning/fanout tuning. Advisory, read-only.
/deliberation:ask-allAsk GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then synthesize and compare. Zero cross-contamination.
/deliberation:ask-geminiGet Gemini second opinion on a question or current work. Single-shot, advisory, no contamination. Model pinned per call.
/deliberation:ask-gptGet GPT (Codex) second opinion on a question or current work. Single-shot, advisory, no contamination.
/deliberation:ask-grokGet Grok (xAI) second opinion on a question or current work. Single-shot, advisory, no contamination.
/deliberation:ask-openrouterAsk a single configured OpenRouter model for a second opinion. Advisory only. Single-shot or multi-turn.
/deliberation:codex-loginLog GPT (Codex) in on this machine with a ChatGPT device login - shows a link and a one-time code. For remote or headless sessions (Claude Code on the web). No question is sent to GPT.
/deliberation:consensusArbiter-mediated consensus - GPT + Gemini + Grok (plus any configured OpenRouter delegates) review while Claude commits a blind verdict, adjudicates, and synthesizes. Converges only with cross-model agreement. Driven by the consensus-step engine.
/deliberation:dashboardStart (or `restart`) the local read-only dashboard (live and past deliberation runs as state graphs, config, health, stats, analyzer) and print its URL. Needs a browser on the same machine.
/deliberation:doctorCheck deliberation's health - config, provider CLIs, sessions/debug, and path drift - and suggest fixes. Read-only; never changes anything.
/deliberation:grok-filesList, prune, or gc Grok (xAI) uploaded files. Cleanup for bridge-owned uploads only.
/deliberation:helpShow how to use deliberation here - what each command does, when to reach for it, and real prompts you can paste right now. Read-only.
/deliberation:reload-mcpGracefully cycle dashboard and audit MCP processes after deliberation is updated.
/deliberation:setupConfigure deliberation with Codex (GPT), Gemini, Grok, and OpenRouter MCP servers
/deliberation:uninstallUninstall deliberation (remove MCP config and rules)
deliberation-geminiruns: node ${CLAUDE_PLUGIN_ROOT}/server/gemini/index.js
deliberation-grokruns: node ${CLAUDE_PLUGIN_ROOT}/server/grok/index.js
deliberation-openrouterruns: node ${CLAUDE_PLUGIN_ROOT}/server/openrouter/index.js
deliberationruns: node ${CLAUDE_PLUGIN_ROOT}/server/mcp/index.js
Review and maintain reusable Terraform modules against a written profile of the module family's rules: pull request review with one verdict, findings-only review of a local change, and a maintainer skill that makes the change.
8 skills
Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.
1 skill · 1 command
Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.
1 skill
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
AI memory system — mine projects and conversations into a searchable palace. 47 MCP tools, auto-save hooks, guided setup.
3 skills · 6 commands · 1 MCP server · hooks
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.