35 tagged consensus, measured the same way as everything else here.
Browse within: gpt 9claude-plugin 8Multi-Agent 7
google-research/google-research
Skill Claude CodeCodex
A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a comparable-company cross-check, and the analyst-consensus view.
Skill Claude CodeCodex
Summarize the sell-side view on an equity — analyst price targets, forward EPS/revenue estimates and ratings — and corroborate it against recent guidance and estimate revisions from the web.
Skill Claude CodeCodex
A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a comparable-company cross-check, and the analyst-consensus view.
Skill Claude CodeCodex
Alias for Codex-led consensus plan review adapted from the Claude Consensus plugin. Use when the user invokes claude-consensus from Codex.
Skill Claude CodeCodex
Alias for Codex-led multi-model code review. Use when the user invokes code-review, asks for code review with multiple models, or requests consensus code review.
Skill Claude CodeCodex
Codex-led multi-model plan review using Claude Consensus style. Use when the user invokes consensus-plan-review, claude-consensus plan review, multi-model plan review, or asks to run plan-review from Codex.
Skill Claude CodeCodex
Squash-merge a worktree branch into the target branch with a structured commit message. Use after audit consensus and retrospective completion.
Skill Claude CodeCodex
Session orchestrator for the consensus-loop — reads handoff, picks unblocked tasks, distributes to parallel workers, tracks agent assignments, manages correction cycles via SendMessage. Use when starting a work session with pending tasks, distributing implementation work, or reviewing completed worker output.
Skill Claude CodeCodex
Design tasks into tracks with work breakdowns and execution order. Also writes and maintains PRDs (Product Requirements Documents) — when a user requests a feature, analyzes it, adds it to the PRD, then decomposes into work breakdowns. Use for new feature planning, PRD writing, architecture changes, multi-track…
Skill Claude CodeCodex
Operate the engine's distributed substrate — openraft consensus with automatic failover, multi-Raft groups, online resharding (ownership move / hibernate / rehydrate), cross-shard 2PC, and the per-tenant catalog — plus the scope-gated ADMIN tier: RBAC policy administration and ops backup/restore. Use when scaling the…
Skill Claude CodeCodex
Review code with multiple specialist subagents, then use gemot to find where they disagree and why. Requires gemot MCP server configured.
Skill Claude CodeCodex
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
TokonoMix/tokonomix-council-mcp
Skill Claude CodeCodex
Cross-check a high-stakes answer across multiple frontier models (Claude + GPT + Gemini side by side, then a judge synthesizes) when one model is not enough — proactively offer it (don't wait to be asked) before anything irreversible or customer-facing: DB migrations, customer-facing or legal/compliance statements…
TokonoMix/tokonomix-council-mcp
Skill Claude CodeCodex
Direct HTTP access to the Tokonomix AI gateway — OpenAI- and Anthropic-compatible endpoints for chat, image generation, image editing, vision consensus, embeddings, audio transcription and reranking, with EU data-residency routing through one key. Use when building an app, an agent framework, or a CI pipeline without…