agent agents

SWE-agent/mini-swe-agent

Agent

!!! note "InteractiveAgent class".

MrLesk/Backlog.md

Agent Claude Code

Use this agent when you need to manage project tasks using the backlog.md CLI tool. This includes creating new tasks, editing tasks, ensuring tasks follow the proper format and guidelines, breaking down large tasks into atomic units, and maintaining the project's task management workflow. Examples: Context: User wants…

Tencent/AI-Infra-Guard

Agent

An automation procedure for deploying a Model Context Protocol (MCP) program from source code. MCP is a standard way for an AI client to connect to tools or data services.

Tencent/AI-Infra-Guard

Agent

A static security-audit agent for MCP projects. Static analysis examines source code without running it, focusing on vulnerabilities that could be reached through network inputs.

Tencent/AI-Infra-Guard

Agent

A security-review agent that checks vulnerability reports for real, reproducible threats and filters out false positives. A false positive is an alleged problem that is not actually exploitable or harmful in the stated environment.

netease-youdao/LobsterAI

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

netease-youdao/LobsterAI

Agent

Compare two outputs WITHOUT knowing which skill produced them.

netease-youdao/LobsterAI

Agent

Evaluate expectations against an execution transcript and outputs.

vercel-labs/open-agents

Agent

This is a Turborepo monorepo for "Open Agents" - an AI coding agent built with AI SDK.

vercel-labs/open-agents

Agent

Detailed coding conventions, tool implementation patterns, and common patterns for the Open Agents codebase.

vercel-labs/open-agents

Agent

Audited against the Vercel React Best Practices (57 rules, 8 categories). Findings are ordered by impact.

OpenSenseNova/SenseNova-Skills

Agent

A planning agent for research projects that turns a question and its confirmed scope into a structured execution plan.

OpenSenseNova/SenseNova-Skills

Agent

A research agent that gathers evidence through multiple rounds of searching and saves the results in a structured evidence.json file.

OpenSenseNova/SenseNova-Skills

Agent

A review agent for checking research reports and finished content against their required structure, evidence, and source boundaries. It handles both individual evidence reports and assembled final documents.

WuKongIM/WuKongIM

Agent

The Issue Agent behaves like a senior engineer embedded in a GitHub Issue. For an authorized, sufficiently concrete, low-risk Bug it attempts to reproduce the symptom, records its evidence, finds the root cause, makes the smallest repair, runs tests, and opens one complete Draft PR. A human always reviews and merges.

WuKongIM/WuKongIM

Agent

Issues and PRDs for this repository live as GitHub issues. Use the gh CLI from this checkout so the repository is inferred from git remote.

WuKongIM/WuKongIM

Agent

The Review Agent is an administrator-invoked senior reviewer for pull requests targeting main. The model reviews and adjudicates without changing code or merging. No model review starts until a current repository administrator posts the exact @review-agent review command.

archestra-ai/archestra

Agent Claude Code

Checks the claims in a summary and returns whether they hold. Use after summarizing.

evalstate/fast-agent

Agent

Run shell and filesystem tools in local, Docker, Hugging Face, or custom environments.

evalstate/fast-agent

Agent

Plugins package reusable slash commands such as /find, /peek, or /edit-last, post-user-turn displays, or both. They install into the active project or global fast-agent home under plugins/ and are enabled by name from that scope's configuration file.

evalstate/fast-agent

Agent

Agent "prompting" from evalstate/fast-agent, covering prompting agents, sending messages, using generate() and multipart content, using structured() for typed responses and define your expected response structure.

proma-ai/Proma

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

proma-ai/Proma

Agent

Compare two outputs WITHOUT knowing which skill produced them.

proma-ai/Proma

Agent

Evaluate expectations against an execution transcript and outputs.