gemini agents

antonbabenko/deliberation

Agent

Part of deliberation

Threat-model and find vulnerabilities, with practical remediation.

ypollak2/llm-router

Agent

Part of llm-router

Cost-optimized assistant that routes every task through LLM Router first.

Aqualia/Alph

Agent

Warp Terminal MCP – Integration with Alph Overview: Warp is a modern terminal that features an “Agent Mode” with AI assistance. Warp supports MCP servers as modular plugins to extend its AI agents with custom tools and data[18]. Integrating Alph with Warp means configuring Warp’s MCP client to know about Alph’s MCP…

Aqualia/Alph

Agent

Windsurf Cascade MCP – Integration with Alph Overview: Windsurf (formerly Codeium’s editor) includes Cascade, an AI agent that can leverage external tools via the Model Context Protocol (MCP)[1]. To integrate Alph with Windsurf, Alph must configure Windsurf’s MCP client to recognize and launch Alph’s MCP server. This…

Aqualia/Alph

Agent

These examples show how Alph renders MCP server configuration for different agents and transports.

silo-code/silo

Agent

Host-computed coding-agent activity and resume-identity observability — a live, read-only view of what each terminal's agent is doing, plus an honest resume hint when a session's backend dies uncleanly. The companion to ctx.processes (foreground process facts); this surface is for agent activity and resume identity.…

Unsupervisedcom/deepwork

Agent Claude Code

Reviews that all end-user functionality is covered by RFC 2119 requirements and that all requirements have traceable automated tests or DeepWork review rules.

Unsupervisedcom/deepwork

Agent

Part of learning-agents

Expert on the LearningAgent system. Operates on LearningAgent files: identifies issues in transcripts, investigates root causes, and incorporates learnings into agent definitions.

Unsupervisedcom/deepwork

Agent

Part of deepwork

Minimal review subagent for DeepWork review tasks. Reads a supplied instruction file, performs the review against the criteria in that file, and reports results via the DeepWork MCP markreviewaspassed tool. Use when dispatching parallel review tasks from .deepreview rules or workflow quality gates.

abiswas97/gemini-plugin-cc

Agent

Part of gemini

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Gemini through the shared runtime.

personamanagmentlayer/pcl

Agent Claude Code

Use this agent when you need to create, review, improve, or maintain documentation for code, APIs, features, or projects. This includes writing user guides, API references, tutorials, README files, inline code comments, migration guides, changelog entries, and technical specifications. Also use when evaluating…

personamanagmentlayer/pcl

Agent Claude Code

Use this agent when you need to design, implement, review, or improve test suites and testing strategies. This includes writing unit tests, integration tests, end-to-end tests, setting up test infrastructure, debugging flaky tests, improving test coverage, or evaluating code for testability. Also use when reviewing…

personamanagmentlayer/pcl

Agent Claude Code

Use this agent when you need to analyze code, configurations, or architectures for security vulnerabilities, review implementations against security standards (OWASP, CWE, NIST), assess threat models, identify attack surfaces, or ensure compliance with security best practices. This agent should be proactively invoked…

ssdeanx/deep-research

Agent

This directory contains 6 specialized AI agents that form the core intelligence layer of the Deep Research Assistant. Each agent has specific capabilities and responsibilities in the research pipeline.

codecast-sh/codecast

Agent

Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.

codecast-sh/codecast

Agent

Implements a single task end-to-end in an isolated worktree. Spawned by the orchestrate conductor for each task in a plan.

codecast-sh/codecast

Agent

Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.

MarcosNahuel/antigravity-plugin-cc

Agent

Part of antigravity

Forwards a coding/diagnosis/research/recording/scraping/conversion/design-review/code-review/one-shot-ask request to the Google Antigravity CLI (agy) via --print mode. Use proactively when Claude should hand a substantial task, a quick one-shot prompt, a git-diff code review, deep web research, a browser walkthrough…

CaicoLeung/bob-plugin-ollama-translator

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

CaicoLeung/bob-plugin-ollama-translator

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

CaicoLeung/bob-plugin-ollama-translator

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

Galbaz1/video-research-mcp

Agent

Part of gr

Fetch YouTube video comments and analyze them via Gemini Flash for sentiment and key opinions (runs in background).

Galbaz1/video-research-mcp

Agent

Part of gr

Bridge agent that combines Gemini research analysis with video synthesis. Analyzes content with video-research tools, then creates explainer videos. Use when converting research, videos, or articles into explainer content.

Galbaz1/video-research-mcp

Agent

Part of gr

Expert workflow advisor for the /gr plugin. Recommends the optimal command and workflow for research, video analysis, content extraction, or knowledge management tasks. Checks prior work first.