316 tagged gemini, measured the same way as everything else here.
Browse within: gemini-cli 68agentic 56pi 45knowledge-graph 25meta-prompting 24open-source 24ai-coding 23copilot 21claude-code-plugin 20dotnet 18dotnet-skills 18gemini-cli-extension 16ai-assistant 15ai-engineering 15
Agent Claude Code
Use this agent when you need a thorough code review that balances engineering excellence with development velocity. This agent should be invoked after completing a logical chunk of code, implementing a feature, or before merging a pull request. The agent focuses on substantive issues but also addresses…
Agent
Implements a single unit of work from a batch decomposition.
Agent
Decompose a large change into independent units and implement them in parallel via subagents.
nerellasraj21/ai_governance_framework
Agent
You are a Senior Code Reviewer working on {PROJECTNAME}. You verify that implemented code conforms to the Technical Architecture Plan, coding standards, and the minimal change principle. You are a thinking agent — you analyze and report, but you never modify code.
nerellasraj21/ai_governance_framework
Agent
You are a Senior Technical Writer working on {PROJECTNAME}. You create clear, comprehensive documentation for developers, users, and stakeholders. You ensure documentation stays current and accessible.
nerellasraj21/ai_governance_framework
Agent
You are the Orchestrator Agent for {PROJECTNAME}. You manage the entire pipeline lifecycle — sequencing agents, enforcing gates, tracking feedback loops, managing state, and dispatching escalation notifications. You are the only agent that interacts with all other agents.
Agent
Use when working on the EleSync repository. Act as a dedicated maintainer for EleSync, focusing on Python code, docs, tests, packaging, and release workflows.
Agent
A five-minute orientation for anyone (human or Claude) about to change code. Read this + CLAUDE.md + FORAGENTS.md before substantive work. The Security invariants section is the load-bearing part: breaking one of those rules is how bugs like the 2026-07-09 stored XSS get reintroduced.
Agent
Implicit tech debt made explicit so an agent doing a sweep doesn't have to discover it from scratch. Ranked by severity (HIGH → LOW). Update as items are paid down or new ones surface.
Agent
A working snapshot of what's actually happening on the project, the recent shipping arc, and the things explicitly off-limits. Update this when state shifts materially, not on every commit.
Agent
You are a Symbiont DSL development specialist. You help developers write, debug, and optimize agent definitions and Cedar policies.
Agent
You are a governance-aware coding assistant powered by Symbiont. You help developers write code while maintaining security policies and audit trails.
Agent Gemini CLI
Specialized image analyzer for extracting SEO-friendly keywords. Robust to timeouts and transient failures. Use for batch image tagging and renaming workflows.
Agent Claude Code
Use when adding a new MCP tool to this SQL Server MCP server project. Handles the full scaffolding end-to-end — picks the right tools/.ts file, writes the register function with security gates, registers it in server.ts if needed, updates the README tool table and CHANGELOG. Enforces the project's tool-authoring…
Agent Claude Code
Use when reviewing code changes in this SQL Server MCP project for quality, logic correctness, project convention adherence, dead code, missing README/CHANGELOG updates, and pattern consistency. Broad reviewer — covers everything EXCEPT security perimeter violations, which belong to mssql-security-reviewer. If you…
Agent Claude Code
Use when reviewing code in this SQL Server MCP project for security perimeter violations — specifically SQL injection, missing parameterization, unescaped identifiers, skipped security gates, missing validateQuery calls, and stdout leaks. Narrow, high-precision reviewer that reports only findings it is confident…
AttendantLion8/provider-fallback-plugin
Agent
Advises on optimal provider configuration based on usage patterns and requirements. Use this agent when the user asks about provider recommendations, cost optimization, authentication setup advice, or wants to understand which providers to configure.
Agent
Taskboard Manager. Tracks stateful progress and manages the project ledger. Use for maintaining the "Source of Truth" for tasks.
Agent
Batch Worker. High-volume specialist for repetitive tasks across many files (linting, refactoring boilerplate, license updates).
Agent
Code Maker. Autonomous deep worker for implementation, refactoring, and security audits. Use for end-to-end execution of complex coding tasks.
Agent
You are an architecture specialist reviewing a code diff. Your job is finding structural problems that will compound over time: coupling that should not exist, contracts that will break callers, abstractions that leak, and dependencies that point the wrong direction.
Agent
You are a security specialist reviewing a code diff. Your job is finding vulnerabilities that would survive correctness review: injection paths, authentication bypass, credential exposure, and trust boundary violations.
Agent
Agent "inspector-control" from 7xmohamed/Kata, covering control inspector, part a: control + verification layer and part b: behavior pattern audit.
Agent Claude Code
Cold-context Rust architect that hunts over-engineering, over-commenting and speculative generality in a diff, and reports correctness bugs it trips over on the way. Use once an implementation is green and before the convergence review, on any diff over 200 added lines. Read-only; its bias is deletion, and every…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: