Agents

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

asesor

1489

gmoncor/agentic-engineering-framework

Agent Claude Code

Analiza un problema, evalua opciones y recomienda la mejor solucion con trade-offs. Consultor tecnico de solo lectura.

not rated 5 14d ago A 27 tokens

orchestrator

1490

mikailustuner/OmniRule

Agent Claude Code

Main dispatch agent for OmniRule. Routes every task to the right specialist agent or combination of agents. Always the entry point. Use for ANY task — it decides who does what.

not rated 5 3mo ago A 40 tokens

context-docs-generator

1491

Baughn/machine-config-template

Agent Claude Code

Use this agent when you need to create or update documentation in the context/ directory based on code analysis or online documentation. This includes situations where: existing documentation is missing, incomplete, or outdated; new features or APIs need to be documented; you need to understand a library or framework…

not rated 5 8mo ago A 418 tokens original MIT

mars-mx/vibesaas

Agent Claude Code

Use this agent when you need assistance with Vercel deployments, configuration, or troubleshooting. This includes: deploying Next.js projects to Vercel, setting up backend functions, configuring WAF and security features, resolving deployment errors, optimizing build settings, managing environment variables, setting…

not rated 5 7mo ago A 404 tokens original MIT

backend-test-writer

1493

elieteyssedou/clean-boilerplate-26

Agent Claude Code

Use this agent when you need to write, review, or improve backend automated tests using Mocha and Sinon. Examples: Context: User has just implemented a new GraphQL resolver for creating components and needs comprehensive test coverage. user: 'I just added a createComponent resolver that validates input, calls the AI…

not rated 5 10mo ago A 0 tokens

clojure-specialist

1494

sadjow/home-manager

Agent Claude Code

Handle a bounded Clojure, ClojureScript, or JVM-interop implementation only after the user explicitly authorizes delegation.

not rated 5 changed 3d ago A 32 tokens

data-engineer

1495

sankalpsharmaa/claude-config-public

Agent Claude Code

Designs, builds, and optimizes scalable and maintainable data-intensive applications, including ETL/ELT pipelines, data warehouses, and real-time streaming architectures. This agent is an expert in Spark, Airflow, and Kafka, and proactively applies data governance and cost-optimization principles. Use for designing…

not rated 5 1mo ago A 80 tokens

deomiarn/claude-setup-template

Agent Claude Code

Generate Midjourney v7 prompts for custom brand photography. Analyzes brand colors, content, SEO to create consistent art direction. Use for AI image generation, brand photography prompts, visual content planning.

not rated 5 9mo ago A 48 tokens

claude-crawler

1497

d-mariano/spicyclaude

Agent Claude Code

Use this recusrive agent to update CLAUDE.md files either on-demand or after any updates to features, data-flow, or infrastructure.

not rated 5 1mo ago A 34 tokens original MIT

fable-planner

1498

casualsav/fable-bench

Agent Claude Code

Fable 5 planner for the /fable skill. Invoked once by /fable with a plan brief — intent, task verbatim, session constraints, file map, pasted load-bearing code, and 1–3 open questions — and returns the plan: numbered steps with risks, checkpoints, assumptions. Resumed at task end for the warm diff-review…

not rated 5 15d ago A 147 tokens original MIT

tdd-guide

1499

alpadev-fx/agnostic

Agent Claude Code

Test-driven development specialist. Use when writing new features to ensure proper test coverage and structure.

not rated 5 1mo ago A 22 tokens

completion-agent

1500

armenr/ctx-fieldbook

Agent Claude Code

Firsthand gate-reproduction leg — the FIRST verifier at wave close, before the independent merge-gate verifier and before the orchestrator integrates or commits. Reruns the quality gates itself ({{BUILDCMD}} · {{LINTCMD}} · {{TESTCMD}} · {{FMTCMD}}), proves IMPL→WIRED reachability, reads the fenced diff, and returns a…

not rated 5 1mo ago A 126 tokens

workspace-sync

1501

41fred/ace-level1

Agent Claude Code

Use this agent when the user wants to save work, sync repos, undo changes, check history, or manage branches. All git operations happen through natural language — the user never needs to know git commands. Examples: Context: User finished working and wants to save. user: "Save my work" assistant: "I'll use…

not rated 5 2mo ago A 233 tokens original MIT

operator-interviewer

1502

gertsylvest/meta-team

Agent Claude Code

Extracts operator direction efficiently using structured discovery — gap-fill synthesis, option-led questions, progressive disclosure. Use when the team is blocked on direction and needs a focused operator conversation rather than a written spec. Operates in two phases: (1) produce a direction brief for the operator…

not rated 5 1mo ago A 74 tokens original MIT

backend-developer

1503

eimis1990/inzone

Agent Claude Code

Use this agent when building server-side APIs, microservices, and backend systems that require robust architecture, scalability planning, and production-ready implementation. Specifically:\\n\\n \\nContext: A project needs a new RESTful API service with database persistence, authentication, and caching for handling…

not rated 5 3mo ago A 554 tokens original MIT

Explore

1504

AndrewSB/dotfiles

Agent Claude Code

Fast read-only search agent for locating code. Use it to find files by pattern (eg. "src/components//.tsx"), grep for symbols or keywords (eg. "API endpoints"), or answer "where is X defined / which files reference Y." Do NOT use it for code review, design-doc auditing, cross-file consistency checks, or open-ended…

not rated 5 1mo ago A 0 tokens

triage-researcher

1505

Aibier/claude-em-toolkit

Agent Claude Code

Use when an EM needs to scan/triage across multiple repos, services, or large result sets in parallel — e.g. "which of these 5 repos reference this deprecated API", "find all TODOs related to X across the org's services". Read-only, keeps the dispatching session's context clean.

not rated 5 3mo ago A 70 tokens original MIT

code-reviewer

1506

dinhquan/claude-ios-toolkit

Agent Claude Code

Reviews Swift/SwiftUI code for quality, security, and performance. Use after any code changes.

not rated 5 7mo ago A 24 tokens

helldivers

1507

ryantlee25-droid/spectrum-protocol

Agent Claude Code

Product research and problem identification agent. Validates that a problem is real, significant, and worth solving before solution exploration. Produces a structured Problem Brief grounded in evidence-based discovery frameworks. user: "what problems should we focus on for our dev tools product?" assistant: uses…

not rated 5 5mo ago A 219 tokens original MIT

code-reviewer

1508

tlipoca9/devgen

Agent Claude Code

Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter.

not rated 5 4mo ago A 39 tokens copy · 100% MIT

ui-reviewer

1509

shamimfahad/adlc-toolkit

Agent Claude Code

Runtime UI/UX review of a change. Starts the app's dev server and drives a browser to confirm the changed UI renders, the flows work, the interaction states are correct (disabled/loading/error/empty, not just the happy view), and the result matches the design and UI acceptance criteria — the things static review…

not rated 5 1mo ago A 174 tokens

code-analyzer

1510

zsutxz/ClaudeLearning

Agent Claude Code

Use this agent when you need to analyze code structure, identify patterns, or understand codebase architecture. Examples.

not rated 5 1mo ago A 0 tokens original MIT

chapter-writer

1511

QQQingyu/story-snack

Agent Claude Code

An agent that expands a chapter outline into a complete serial-fiction chapter while following the project's style and character files.

not rated 5 5mo ago A 28 tokens original MIT

documentarian

1512

JansenAnalytics/claudex

Agent Claude Code

Write or update inline docs, README sections, and API references after a code change. Use when code has been added/modified and the docs need to catch up, or when a module is undocumented.

not rated 5 2mo ago A 43 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: