Skill Claude CodeCodex
Audit Claude Code configuration for issues, overlaps, unused components, update status, and misconfigurations. Use when the user (1) asks to check or audit their setup, (2) wants to find duplicate or conflicting skills, hooks, plugins, or rules, (3) asks what is broken or needs cleanup, (4) wants to check Claude Code…
Skill Claude CodeCodex
Interact with Slack via the Web API. Read, summarize, search, post messages, react, pin, and manage channels. Use when the user (1) shares a Slack URL, (2) asks to read or summarize a channel, (3) searches Slack messages, (4) asks to send/post a message, (5) asks to react to or pin a message, (6) looks up a user, or…
Skill Claude CodeCodex
Reports which skills, hooks, rules, plugins, and MCP tools were activated during a Claude Code prompt or session. Use when the user asks "what was used", "which skills ran", "show me what fired", or invokes /used. Also triggers when the user wants transparency into Claude's behavior for a given prompt.
Plugin Claude Code
Wraps gemini-mcp into a Claude Code plugin so Gemini acts as a second opinion: validator/challenger/researcher/summarizer/reviewer subagents, auto-trigger hooks, and 9 task-oriented skills.
Agent
Use proactively before destructive operations, when evaluating architectural choices, or when the main agent appears stuck in a pattern. Devil's advocate that argues at least 2 alternative approaches and 1 reason the current path is wrong. Returns structured JSON {alternatives, objections, mustaddress}.
Agent
Use proactively when a question involves post-training-cutoff information, live API docs, recent CVEs, library releases, or any claim that needs a primary source. Performs search-grounded research and deep research via Gemini. Never opines without a citation. Returns answer + citations.
Agent
Use proactively when finalizing a diff or PR for a generalist third-reviewer pass that the other agents do not cover: security, threading correctness, library/version drift, doc accuracy, dead code, and complexity. NOT for research (use gemini-researcher), claim validation (use gemini-validator), or devil's-advocate…
Agent
Use proactively at session start (BUILDRISKMAP) and before context compaction (SUMMARIZESESSIONSTATE). Compresses session history into structured summaries preserving decisions, discarded alternatives, and unresolved debt. Writes risk maps for new repositories.
Agent
Use proactively after a plan is finalized, after Claude claims a task is done, or before a destructive change. Validates the artifact against the original ask and flags gaps, hallucinations, and missed acceptance criteria. Returns structured JSON {verdict, gaps, hallucinations, nextactions}.
Command
Turn off Gemini grounding on every prompt (the plugin will only ground when prompts contain post-cutoff keywords like 'latest version of X' or 'CVE-YYYY-NNN').
Command
Re-enable Gemini grounding on every prompt (it is on by default; this only matters if you previously turned it off).
Command
Get Gemini to argue against a decision or propose alternatives.
Command
Diagnose whether the Gemini MCP server and the subagent grounding path are working in this session.
Command
Research a topic using Gemini's search-grounded or deep research capabilities.
Command
Get a Gemini second opinion on a plan, diff, or claim.
Hook
Runs when a session starts on startup, executing session-start-risk-map.sh. From azmym/gemini-plugin.
Hook
Runs when you submit a prompt, before the agent sees it, executing user-prompt-grounding.sh. From azmym/gemini-plugin.
Hook
Runs before the agent uses a tool for Bash and ExitPlanMode tool calls, executing pre-destructive-bash.sh and plan-complete.sh (2 commands). From azmym/gemini-plugin.
Hook
Runs after a tool call finishes for Write and Edit tool calls, executing design-review.sh. From azmym/gemini-plugin.
Hook
Runs before the context is compacted, executing pre-compact-summary.sh. From azmym/gemini-plugin.
Hook
Runs when the agent finishes a response, executing stop-done-claim.sh. From azmym/gemini-plugin.
Hook
Runs when a subagent finishes for gemini-validator, gemini-challenger, gemini-researcher, gemini-summarizer and gemini-reviewer tool calls, executing subagent-verdict-handler.sh. From azmym/gemini-plugin.
Skill Claude CodeCodex
Generate music (Lyria 3) or synthesize speech (Gemini TTS, single or multi-speaker). Use for soundtracks, voiceovers, demo narration, notification sounds, or audio branding.
Skill Claude CodeCodex
Get a second opinion from Gemini via text generation or multi-turn chat. Use for code review, design critique, sanity-checking before commit, or when Claude wants another perspective on a complex decision.