Plugin Claude Code
Plugin marketplace listing 1 plugin: ask-llm.
16 7d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
AGENTS.md instructions for Lykhoyda/ask-llm, covering project agent memory and maintaining this file.
16 7d ago A 1,120 tokens
original MIT
ask-llm
03Plugin Claude Code
AI-to-AI collaboration — review code and debate plans across Codex, Grok, Antigravity, Ollama, and Gemini.
16 7d ago A
tokens not measured
original MIT
codex
04MCP server Claude CodeCodexCursor +2
MCP server for OpenAI Codex CLI integration - for Claude IDE and other IDEs. Runs locally from the @ask-llm/codex-mcp npm package.
16 7d ago A
tokens not measured
original MIT
Agent
Runs a focused Google Antigravity code review with confidence-based filtering and source verification. Use for a subscription-backed second opinion on code changes or diffs.
16 7d ago A 37 tokens
original MIT
Agent
Coordinates multi-LLM brainstorming by forming an independent host-model view before consulting external providers, then cross-checking and synthesizing evidence, disagreements, and actionable recommendations.
16 7d ago C 38 tokens
original MIT
Agent
Runs a focused Codex code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.
16 7d ago A 36 tokens
original MIT
Agent
Verifies the assistant's claims against actual state using OpenAI Codex with a read-only tool surface. Decomposes the assistant's last message and the diff into atomic claims, proves or disproves each with deterministic evidence, returns STATUS + CONFIDENCE on a five-grade ladder. Use when you want to confirm what was…
16 7d ago A 99 tokens
original MIT
Agent
Reviews code changes in an isolated, read-only context configured to request Fable and reports only source-verified, high-confidence correctness findings.
16 7d ago A 32 tokens
original MIT
Agent
Runs a focused Gemini code review with confidence-based filtering and source verification. Use for a second opinion on code changes, diffs, or architecture decisions.
16 7d ago A 35 tokens
original MIT
Agent
Runs a focused Grok review through the metered xAI API, then verifies findings against source. Never changes billing or substitutes another model.
16 7d ago A 33 tokens
original MIT
Agent
Runs a focused local Ollama code review with confidence-based filtering and source verification. Runs entirely locally, so no project data leaves the machine.
16 7d ago A 33 tokens
copy · 88% MIT
sol-reviewer
13Agent
Coordinates an isolated, read-only code review explicitly pinned to OpenAI GPT-5.6 Sol and reports only source-verified, high-confidence correctness findings.
16 7d ago A 35 tokens
original MIT
Stop
14Hook
Runs when the agent finishes a response, executing codex-pair-stop-gate.mjs via node. From Lykhoyda/ask-llm.
16 7d ago A
tokens not measured
original MIT
PostToolUse
15Hook
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing codex-pair-watch.mjs via node. From Lykhoyda/ask-llm.
16 7d ago A
tokens not measured
original MIT
SessionStart
16Hook
Runs when a session starts, executing codex-pair-session.mjs via node. From Lykhoyda/ask-llm.
16 7d ago A
tokens not measured
original MIT
SessionEnd
17Hook
Runs when a session ends, executing codex-pair-session.mjs via node. From Lykhoyda/ask-llm.
16 7d ago A
tokens not measured
copy · 89% MIT
Hook
Runs when you submit a prompt, before the agent sees it, executing codex-pair-prompt-drain.mjs via node. From Lykhoyda/ask-llm.
16 7d ago A
tokens not measured
copy · 86% MIT
Skill Claude CodeCodex
Get a second opinion from Google Antigravity (agy) on your current code changes. Analyzes staged/unstaged diffs and returns prioritized findings. Use when the user asks to "review with Antigravity", "Antigravity code review", or "ask agy to check my code".
16 7d ago A 67 tokens
original MIT
Skill Claude CodeCodex
Send a topic to all external providers (Gemini, Codex, Grok, Ollama, Antigravity) concurrently after the current host model forms an independent view. Use when the user wants an all-provider brainstorm with synthesis and explicit unavailable-provider reporting.
16 7d ago A 56 tokens
original MIT
brainstorm
21Skill Claude CodeCodex
Send a topic to an explicit multi-model panel, then synthesize findings with truthful provider, harness, and model attribution. Usage /brainstorm [participants] . Defaults to antigravity,codex. Preferred Grok route uses Cursor Agent with an exact catalog ID.
16 7d ago A 59 tokens
original MIT
codex-image
22Skill Claude CodeCodex
Generate an image via OpenAI's gpt-image-2 model through the Codex CLI. Use when user asks to "generate an image", "create an image", "make a picture of", "render a graphic", "draw something", or wants visual content via Codex. Requires codex-cli >= 0.125.0 with the imagegeneration feature flag enabled (stable +…
16 7d ago A 93 tokens
original MIT
Skill Claude CodeCodex
Acknowledge a codex-pair finding by its 16-character hash and a user-owned reason. Use when the user wants to suppress a repeated finding reminder or defer a host gate where supported.
16 7d ago A 47 tokens
original MIT
Skill Claude CodeCodex
Pause codex-pair for this project without removing .codex-pair/context.md. Writes the shared .codex-pair/state/paused sentinel. Use during noisy refactors, hook dogfooding, or other temporary review pauses.
16 7d ago C 56 tokens
original MIT