Agents

Subagents with their own prompt and tools. Injected whole, so what you see in the token column is what every session pays.

analyst

409

RchGrav/claudebox

Agent

When this command is used, adopt the following agent persona.

not rated 1.1k +3 1y ago A 0 tokens original MIT

MoizIbnYousaf/Ai-Agent-Skills

Agent

Use this agent to gather codebase context for prompt transformation. Explores relevant files, finds similar implementations, identifies patterns to reference, and discovers tech stack constraints. Returns actionable context that makes transformed prompts specific to THIS codebase, not generic advice. Context: User…

not rated 1.1k 18d ago A 354 tokens original MIT

asd-ste100

411

PostHog/posthog.com

Agent

Use when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and misreading has a real cost, or when text reads as dense, hedged, or easy to misparse. Triggers: disambiguate, STE100 rewrite, apply Simplified…

not rated 1.1k yesterday A 99 tokens

agentic-workflows

412

mongodb-js/mongodb-mcp-server

Agent

GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.

not rated 1.1k +2 yesterday A 24 tokens copy · 100% Apache-2.0

report-writer

413

pashov/skills

Agent

Role: Read the completed fuzzing suite outputs (coverage, corpus, campaign logs, properties, handlers) and produce the final report.md. This agent runs AFTER forge build and the FoundryTester sanity test have already passed — it is a pure synthesis/reporting step that does not modify suite files.

not rated 1.1k +8 1mo ago A 0 tokens original MIT

withkynam/vibecode-pro-max-kit

Agent Claude Code

UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after completing EXECUTE mode to reconcile deviations and capture learnings.

not rated 1.1k +7 2mo ago A 36 tokens original MIT

helper

415

affaan-m/agentshield

Agent

General helper agent that reads user input and fetches URLs for processing. Parses HTML content from web pages.

not rated 1.1k +7 1mo ago A 23 tokens original MIT

RetroPilot

416

PharMolix/OpenBioMed

Agent

Autonomous Retrosynthetic Tree Search Loop. Continuously expands nodes, checks vendors via AI models, and backpropagates until the target is solved or interrupted.

not rated 1.1k 1mo ago A 36 tokens original MIT

subagents-research

417

canwhite/Krebs

Agent

A research agent for the pi-subagents and pi-tasks projects, tools for coordinating smaller software agents and tasks. It provides an overview of their structure and how they work.

not rated 1.1k 7d ago A 0 tokens

analyzer

418

Onelevenvy/flock

Agent

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

not rated 1.1k +1 1mo ago A 0 tokens copy · 100% Apache-2.0

agentlas-ai/Agentlas-OS

Agent Claude Code

Use this agent when the user asks for /meta-agent, a single agent builder, multi-agent team builder, or packaging existing agents into Agentlas architecture.

not rated 1.1k +5 2d ago A 38 tokens original Apache-2.0

explainer

420

mohi-devhub/antivibe

Agent

You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.

not rated 1.1k +4 1mo ago A 0 tokens original MIT

log-analyzer

421

huangjia2019/claude-code-engineering

Agent Claude Code

Analyze log files and extract actionable insights. Use when troubleshooting issues or investigating incidents.

not rated 1.1k +2 1mo ago A 20 tokens

domain

422

shaps80/SwiftUIBackports

Agent

How engineering skills should consume this repo's domain documentation.

not rated 1.1k 2mo ago A 0 tokens original MIT

sales-strategy

423

zubair-trabzada/ai-sales-team-claude

Agent

You are the Outreach Strategy Subagent, one of 5 parallel subagents launched during /sales prospect . Your specific responsibility is evaluating Outreach Readiness, which accounts for 20% of the overall Prospect Score.

not rated 1.1k +6 5mo ago A 0 tokens original MIT

FabricAppDev

424

microsoft/skills-for-fabric

Agent ✓ vendor

Build full-stack applications on top of Microsoft Fabric using Python, ODBC, XMLA, and REST APIs. Use when the request involves building applications connected to Fabric data. Delegates endpoint-specific implementation to specialized skills.

not rated 1.1k +33 8d ago A 48 tokens original MIT

code-simplifier

425

dtsola/xiaoyaosearch

Agent Claude Code

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.

not rated 1.1k 3mo ago A 34 tokens

workflow-keeper

426

daangn/seed-design

Agent Claude Code

A read-only agent that checks workflows in the SEED Design monorepo, a repository containing several connected packages. It protects generated files and checks whether required builds or synchronization steps are missing.

not rated 1.1k changed today A 43 tokens original Apache-2.0

implement-coordinator

427

lee-to/ai-factory

Agent

Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.

not rated 1.1k 7d ago A 44 tokens

open-source-librarian

428

jarrodwatts/claude-code-config

Agent

Use this agent when the user needs to understand open-source libraries, find implementation details in codebases, locate specific source code with GitHub permalinks, research the history or context behind code changes, or get authoritative answers backed by actual code evidence. This agent excels at navigating large…

not rated 1.1k 7mo ago A 0 tokens

e2e-verifier

429

K9i-0/ccpocket

Agent Claude Code

An end-to-end testing agent for Flutter apps, meaning tests that operate the app as a user would on a simulator.

not rated 1.0k 5d ago A 65 tokens original MIT

memory-denied-write

430

tintinweb/pi-subagents

Agent

README: "The disallowedtools field is respected when determining write capability — an agent with tools: write + disallowedtools: write correctly gets read-only memory.".

not rated 1.1k +25 yesterday A 17 tokens original MIT

orchestrator

431

sipyourdrink-ltd/bernstein

Agent

Decomposes goals into parallel tasks, assigns them to CLI coding agents, verifies output, and merges results. Use when a task is too large for a single agent.

not rated 1.0k +2 4d ago A 38 tokens original Apache-2.0

Code Review (Codex)

432

microsoft/agentrc

Agent ✓ vendor

Code review following VS Code contribution standards — correctness, lifecycle, naming, layering, accessibility, and security.

not rated 1.0k +3 9d ago A 26 tokens original MIT

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: