Get a second opinion in Claude Code from GPT, Gemini, and Grok - plus 400+ more models through OpenRouter, including Qwen, Kimi, and DeepSeek.
What's inside
A best-practices skill for Terraform and OpenTofu, for AI coding agents (Claude Code, Cursor, Copilot, Gemini CLI, OpenCode, Codex, Kiro, and more). It helps the agent test code, structure modules, set up CI/CD, and write production infrastructure code.
@antonbabenkoFAQ
deliberation is a Claude Code plugin with 8 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes architect, code-reviewer, debugger. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
> /plugin marketplace add antonbabenko/deliberation> /plugin install deliberation@antonbabenko-deliberation
Repo: antonbabenko/deliberation
Get a second opinion in Claude Code from GPT, Gemini, and Grok - plus 400+ more models through OpenRouter, including Qwen, Kimi, and DeepSeek. Seven domain experts (Architect, Code Reviewer, Security Analyst, and four more) review your plans, find bugs, and debate edge cases until they agree.
Recent blog post: Meet Deliberation: 400+ models is easy, knowing which ones earn a place is hard.
When three models argue, the real bug reveals itself. Round 1 = independent top findings. Round 2 = each model dunks on the others' picks. The disagreement matrix shows where they diverge; the conclusion shows what to actually fix first.
Claude can ask GPT, Gemini, Grok, or any OpenAI-compatible model (via OpenRouter) for help through MCP. The plugin handles the wiring for each provider so you just write the prompt. Each expert has a distinct specialty and can advise or implement.
You can use any subset of the providers. The plugin detects which are configured and routes
accordingly. OpenRouter is advisory-only and config-driven: models are declared in
~/.config/deliberation/config.json (Windows: %APPDATA%\deliberation\config.json; override
with DELIBERATION_CONFIG) and hot-reload without restarting Claude Code.
| What you get | Why it matters |
|---|---|
| 7 domain experts | The right specialist for each problem type |
| GPT, Gemini, Grok, or OpenRouter models | Use your preferred provider(s) |
| Dual mode | Experts analyze (read-only) or implement (write) |
| Auto-routing | Claude detects when to delegate from your request |
| Synthesized responses | Claude interprets expert output, never raw passthrough |
1. Add the marketplace - antonbabenko/agent-plugins
/plugin marketplace add antonbabenko/agent-plugins
2. Install the plugin
/plugin install deliberation@antonbabenko
3. Run setup
/deliberation:setup
Claude now routes complex tasks to your GPT, Gemini, Grok, and OpenRouter experts (Grok and OpenRouter advise; GPT and Gemini can also implement).
Setup is a one-time step. The MCP servers are registered by the plugin manifest, so they load automatically and stay current across updates.
/plugin marketplace update antonbabenko # pull the new version from the marketplace
/reload-plugins # reconnect the MCP servers (or just restart Claude Code)
Updating on non-Claude hosts: hosts that run the standalone server via npx -y @antonbabenko/deliberation-mcp get the latest published version on each fresh resolve. npx
caches resolved packages, so if a host serves an old build, clear the npx cache
(rm -rf ~/.npm/_npx) or pin/refresh the version.
deliberation MCP server (standalone, works with any agents)The orchestration server is also published on its own - npm @antonbabenko/deliberation-mcp, Official MCP Registry name io.github.antonbabenko/deliberation.
One-click install:
Add this to your host's MCP config (most hosts use the mcpServers key):
{
"mcpServers": {
"deliberation": {
"command": "npx",
"args": ["-y", "@antonbabenko/deliberation-mcp"],
"env": {
"XAI_API_KEY": "xai-...",
"OPENROUTER_API_KEY": "sk-or-v1-..."
}
}
}
}
The env block is how you set provider keys outside Claude Code. GPT and Gemini do not read keys here - they use the codex and agy CLIs (logged in separately), so drop those lines if you only use GPT/Gemini. XAI_API_KEY enables Grok; OPENROUTER_API_KEY enables OpenRouter (which also needs models declared in ~/.config/deliberation/config.json - the canonical XDG path, Windows %APPDATA%\deliberation\config.json - or point elsewhere with DELIBERATION_CONFIG). The one-click buttons above cannot carry secrets - add the env block by hand after installing.
Per-host config location and the key it expects:
| Host | Config | Key |
|---|---|---|
| Claude Code | claude mcp add deliberation -- npx -y @antonbabenko/deliberation-mcp (or project .mcp.json) | mcpServers |
| Claude Desktop | ~/Library/Application Support/Claude/claude_desktop_config.json (macOS), %APPDATA%\Claude\claude_desktop_config.json (Windows) | mcpServers |
| Cursor | ~/.cursor/mcp.json (global) or .cursor/mcp.json (project) | mcpServers |
| VS Code | .vscode/mcp.json - note: each entry needs "type": "stdio" | servers |
| Codex CLI | ~/.codex/config.toml - TOML, e.g. [mcp_servers.deliberation] | mcp_servers |
| Gemini CLI | ~/.gemini/settings.json | mcpServers |
| Windsurf | ~/.codeium/windsurf/mcp_config.json | mcpServers |
| Zed | settings.json | context_servers |
| Cline | the extension's MCP settings (Cline panel -> MCP Servers) | mcpServers |
Provider prerequisites are the same as the plugin (see Requirements): the Codex CLI for GPT, agy for Gemini, XAI_API_KEY for Grok, and OPENROUTER_API_KEY plus ~/.config/deliberation/config.json for OpenRouter (Windows: %APPDATA%\deliberation\config.json; override the config path with DELIBERATION_CONFIG).
Tools exposed: ask-all, consensus (the full convergence loop in one call, or a single synthesis pass with synthesizeAlways:true), consensus-step (drive the loop yourself, one action per call), ask-gpt / ask-gemini / ask-grok / ask-openrouter, panel + ask-one (discover the active provider set, then call providers individually - issue them in parallel for visible per-provider progress), analyze (read-only run analytics over the debug log + sessions: per-model latency / tokens + verdict agreement, with advisory tuning suggestions), the seven experts (architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, debugger), and the session tools (session-get / session-revisit / session-annotate). Every result carries ms + the effective reasoningEffort (HTTP providers add token usage). An optional debug log ("debug": { "enabled": true }) records latency / tokens / votes - never prompts or responses. These are server-side, so they work on every MCP host, not just Claude Code (see AGENTS.md).
The package also ships a deliberation-setup bin. Run it once with npx -y --package @antonbabenko/deliberation-mcp deliberation-setup to write a starter ~/.config/deliberation/config.json (it never overwrites an existing one). The plain npx -y @antonbabenko/deliberation-mcp form runs the default bin (the server), which is what your MCP host launches. For host rule wiring, see AGENTS.md and the per-host snippets in examples/.
Beyond the raw MCP config above, deliberation ships native plugin artifacts for four hosts so the experience matches the Claude Code plugin (persona-bearing experts + when-to-delegate guidance, not just bare tools). All of these are generated from the canonical sources by node scripts/sync-hosts.js and committed, so they never drift (a CI drift test enforces it). Each host scans the repo for its own files:
| Host | Native artifacts (in this repo) | Install |
|---|---|---|
| Cursor | .cursor/rules/deliberation.mdc | Use the one-click MCP button above, then copy the .mdc into your project's .cursor/rules/. |
| Codex CLI | plugins/deliberation/ (.codex-plugin/plugin.json + .mcp.json + skills/) and a repo-scoped .agents/plugins/marketplace.json | codex plugin marketplace add antonbabenko/deliberation, then install deliberation from /plugins. |
| Kiro | POWER.md + mcp.json + steering/ (a "Kiro Power") | In Kiro, "Add power from GitHub" -> this repo URL. Submit to the registry at kiro.dev/powers/submit. |
| OpenCode | .opencode/commands/*.md + .opencode/agents/*.md | Add the MCP server to opencode.json (mcp key, type: "local", command: ["npx","-y","@antonbabenko/deliberation-mcp"]), then copy .opencode/commands/ and .opencode/agents/ into your project. |
Provider credentials work the same as the standalone server (GPT via the Codex CLI, Gemini via agy, XAI_API_KEY for Grok, OPENROUTER_API_KEY for OpenRouter) - set only the providers you use. The MCP server already injects each expert persona server-side, so these native files add the host's command/steering surface, not duplicated logic.
Full per-host install guides: docs/hosts/ - Cursor, Codex CLI, Kiro, OpenCode.
You need at least one provider:
npm install -g @openai/codex, then codex login.agy and login.XAI_API_KEY (get a key at https://console.x.ai).OPENROUTER_API_KEY (get a key at https://openrouter.ai/keys), then declare models in ~/.config/deliberation/config.json (Windows: %APPDATA%\deliberation\config.json; override with DELIBERATION_CONFIG). Works with any OpenAI-compatible endpoint (Ollama, vLLM, LM Studio, HuggingFace Inference) - auth is skipped automatically when the key env var is empty.Bundled with the plugin (available once installed):
| Command | Purpose |
|---|---|
/deliberation:setup | Configure Codex/Gemini/Grok/OpenRouter MCP servers + orchestration rules |
/deliberation:help | How to use deliberation on your host, with paste-ready example prompts |
/deliberation:doctor | Health check (config, provider CLIs, sessions/debug, path drift) with fixes; read-only |
/deliberation:consensus | 🔥🔥🔥 Arbiter-mediated GPT + Gemini + Grok + Claude convergence loop |
/deliberation:ask-all | 🔥 GPT + Gemini + Grok (+ configured OpenRouter models) in parallel, synthesized |
/deliberation:ask-gpt | One-shot GPT (Codex) second opinion |
/deliberation:ask-gemini | One-shot Gemini second opinion |
/deliberation:ask-grok | One-shot Grok (xAI) second opinion (advisory-only) |
/deliberation:ask-openrouter | One-shot OpenRouter model second opinion (advisory-only) |
/deliberation:analyze | Analyze recent runs (latency, tokens, verdict agreement) and suggest model/reasoning/fanout tuning (advisory) |
/deliberation:uninstall | Remove MCP config, rules, and aliases |
/deliberation:grok-files | List, prune, or gc Grok-uploaded files (storage + local cache cleanup) |
/setup can also install short aliases (/ask-gpt, /ask-gemini, /ask-grok, /ask-all, /consensus, /analyze) into ~/.claude/commands/. This is opt-in. Existing same-named commands are kept by default; setup asks before overwriting any of them. /deliberation:uninstall removes an alias only if it is byte-identical to the bundled copy.
| Expert | What they do | Example triggers |
|---|---|---|
| Architect | System design, tradeoffs, complex debugging | "How should I structure this?" / "What are the tradeoffs?" |
| Plan Reviewer | Validate plans before you start | "Review this migration plan" / "Is this approach sound?" |
| Scope Analyst | Catch ambiguities early | "What am I missing?" / "Clarify the scope" |
| Code Reviewer | Find bugs, improve quality | "Review this PR" / "What's wrong with this?" |
| Security Analyst | Vulnerabilities, threat modeling | "Is this secure?" / "Harden this endpoint" |
| Researcher | External libraries, docs, best practices | "How do I use X?" / "Find examples of Y" |
| Debugger | Root-cause analysis, minimal fixes | "Why does this crash?" / "Debug this failing test" |
Describe your task. Claude detects when an expert helps and delegates automatically:
You: "Is this authentication flow secure?"
Claude: routes to the Security Analyst, then synthesizes the findings.
You can also ask explicitly: "Ask GPT to review this architecture", "Ask Gemini to...", or "Ask Grok to...". Each expert runs read-only for analysis or with write access to apply fixes, and Claude picks the mode from your request.
Or invoke the slash commands directly - see Commands above.
/ask-gpt, /ask-gemini, /ask-grok, and /ask-all are the quick commands: each dispatches one or three external models, Claude reads the output, and you get one synthesized answer. Single shot, no loop, no peer round.
/consensus is the heavy one. Same parallel dispatch, but with a peer-review round and a multi-round loop that stops only when the models agree. The cost: the orchestrator (Claude) writes the review prompt, casts a vote, decides which objections are real, and runs the loop. Left alone, that setup can quietly rubber-stamp its own plan. Four guards stop that.
See the detailed diagram with bias guards and per-model flow
The four guards:
missing-auth, for example) drops out of the count instead of jamming the loop.The /ask-* commands carry a lighter version of the same rule. The external model only advises: Claude reads the output, applies its own judgment, and owns the synthesized answer. When the models agree, that is input, not a verdict.
/consensus is a thin driver over the core convergence engine (core/consensus-loop.js); the loop mechanics - round counting, the convergence rule, the configurable max-rounds cap, history, and the confidence label - live in the engine, not the command. Each round:
The loop converges when at least one responding external approves, none reject, zero critical issues remain accepted, and Claude adjudicates APPROVE - so Claude cannot self-approve. It otherwise stops at consensus.maxRounds (default 5, configurable) as unresolved. The confidence label reflects how fast it settled (round 1 = high, 2-3 = medium, 4-5 = low).
The same engine backs the entry points other hosts use: the consensus tool (runs the whole loop server-side in one call with a provider arbiter, or a single synthesis pass with synthesizeAlways:true) and consensus-step (drive it yourself, one action per call). See TECHNICAL.md for the taxonomy and the engine contract.
An earlier revision ran an extra "Stage 2" anonymized peer cross-review (each model scoring the others' answers blind, adapted from karpathy/llm-council). The engine-driven rewrite removed it to keep one source of truth; it may return as an engine feature.
Full setup and configuration reference lives in SETUP.md. It covers:
read-only) vs implementation (workspace-write), chosen automatically from your request~/.config/deliberation/config.json), the DELIBERATION_CONFIG override, and hot-reloadproviders, models, routing, consensus, sessions, debug - with a minimal exampleaskAll / consensus eligibility, fan-out, reasoningEffort, and arbiter selection; consensus also configures the round cap (maxRounds) and wall-time budget (maxWallMs, default 20 min)providers.defaults.timeout raises the per-call ceiling for every provider at once; providers.<name>.timeout overrides one, and a pinned model's models.<id>.timeout still wins. A rate-limited (HTTP 429) call is retried once, honoring the upstream's Retry-After/consensus loop) and the session-* tools; sessions.captureText (default off) additionally stores provider response bodies (scrubbed)For provider internals, environment variables, and manual MCP setup, see TECHNICAL.md.
Maintained by Anton Babenko - LinkedIn, X/Twitter.
Contributions welcome. See CONTRIBUTING.md for the workflow, commit conventions, and the automated release process.
.agents/
plugins/
marketplace.json
.claude/
.claude-plugin/
marketplace.json
plugin.json
settings.json
.cursor/
rules/
deliberation.mdc
.github/
release/
pre-commit.js
workflows/
automated-release.yml
tag-release.yml
validate.yml
.gitignore
.opencode/
agents/
architect.md
code-reviewer.md
debugger.md
plan-reviewer.md
researcher.md
scope-analyst.md
security-analyst.md
commands/
analyze.md
ask-all.md
ask-gemini.md
ask-gpt.md
ask-grok.md
ask-openrouter.md
consensus.md
.vscode/
extensions.json
settings.json
AGENTS.md
assets/
afewmomentslater.png
agents.png
ask-all.md
ask-all.png
consensus-flow-simple.html
consensus-flow-simple.png
consensus-flow.html
consensus-flow.png
deliberation_512.png
round1.png
round5.png
social-preview.html
social-preview.png
CHANGELOG.md
CLAUDE.md
commands/
analyze.md
ask-all.md
ask-gemini.md
ask-gpt.md
ask-grok.md
ask-openrouter.md
consensus.md
doctor.md
grok-files.md
help.md
setup.md
uninstall.md
config/
config.default.json
config.schema.json
providers.json
CONTRIBUTING.md
core/
analyze.js
consensus-loop.js
debug-log.js
loop-store.js
orchestrate.js
orientation.js
paths.js
prompts/
index.js
provider.js
providers/
antigravity.js
codex.js
grok.js
openai-compatible.js
registry.js
result-cache.js
sessions.js
types.js
docs/
hosts/
codex.md
cursor.md
kiro.md
opencode.md
README.md
examples/
codex.md
cursor.md
kiro.md
README.md
glama.json
LICENSE
mcp.json
package-lock.json
package.json
plugins/
deliberation/
.codex-plugin/
plugin.json
.mcp.json
skills/
architect/
SKILL.md
code-reviewer/
SKILL.md
debugger/
SKILL.md
deliberation/
SKILL.md
plan-reviewer/
SKILL.md
researcher/
SKILL.md
scope-analyst/
SKILL.md
security-analyst/
SKILL.md
POWER.md
prompts/
arbiter.md
architect.md
code-reviewer.md
debugger.md
plan-reviewer.md
researcher.md
scope-analyst.md
security-analyst.md
public-docs/
hosts/
codex.md
cursor.md
kiro.md
opencode.md
README.md
README.md
README.md
renovate.json
rules/
delegation-format.md
model-selection.md
orchestration.md
triggers.md
scripts/
hosts/
_shared.js
codex.js
cursor.js
kiro.js
opencode.js
sync-fallbacks.js
sync-hosts.js
sync-prompts.js
server/
server.json
gemini/
index.js
grok/
cache.js
files-admin.js
glob.js
index.js
lock.js
mcp/
.gitignore
index.js
package.json
README.md
setup.js
openrouter/
config.js
files.js
index.js
routing.js
SETUP.md
steering/
deliberation-triggers.md
deliberation.md
TECHNICAL.md
test/
_helpers.js
bridge.test.js
core-analyze.test.js
core-antigravity.test.js
core-codex.test.js
core-consensus-loop.test.js
core-debug-log.test.js
core-grok.test.js
core-loop-store.test.js
core-mcp-persona.test.js
core-openai-compatible.test.js
core-orchestrate.test.js
core-orientation.test.js
core-paths.test.js
core-prompts.test.js
core-provider.test.js
core-registry.test.js
core-result-cache.test.js
core-review-parse.test.js
core-run-to-convergence.test.js
core-sessions.test.js
core-setup.test.js
core-types.test.js
fixtures/
fake-agy-error.sh
fake-agy-mutates.sh
fake-agy-needs-stdin-eof.sh
fake-agy-nomodel.sh
fake-agy-slow-error.sh
fake-agy-slow.sh
fake-agy-stderr-fail.sh
fake-agy-timeout-recover.sh
fake-agy.sh
gemini-guard.test.js
grok-cache.test.js
grok-dir.test.js
grok-gc.test.js
grok-glob.test.js
grok-lock.test.js
grok-roots.test.js
grok-validation.test.js
grok.test.js
host-artifacts.test.js
http-timeout-ratelimit.test.js
mcp-analyze.test.js
mcp-ask-one.test.js
mcp-consensus-step.test.js
mcp-consensus.test.js
mcp-notifications.test.js
mcp-server.test.js
openrouter-config.test.js
openrouter-files.test.js
openrouter-routing.test.js
openrouter.test.js
redirect-invariant.test.js
standalone-timeout-config.test.js
sync-fallbacks.test.js
tsconfig.json
version.json© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic