Agents

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

AGENTS

433

NVIDIA/cuopt

Agent ✓ vendor

../AGENTS.md.

not rated 1.0k yesterday A 0 tokens copy · 100% Apache-2.0

claude

434

manycoretech/aholo-viewer

Agent

Use these instructions when Claude is helping a user integrate the public @manycore/aholo-viewer npm package into a browser application.

not rated 1.0k +4 yesterday A 0 tokens original MIT

example-generator

435

galkahana/PDF-Writer

Agent Claude Code

Creates example test files for PDF-Writer community requests from GitHub issues or email content.

not rated 1.0k 2mo ago B 20 tokens original Apache-2.0

research-agent

436

SterlingChin/marvin-template

Agent Claude Code

Web research with two modes: quick (simple lookups) and deep (multi-source synthesis). Use quick for fact-finding, deep for content creation or complex topics.

not rated 1.0k +2 17d ago A 37 tokens original MIT

freekmurze/dotfiles

Agent

Use this agent when you need to implement new features in a Laravel application, including creating models, controllers, migrations, routes, views, and associated business logic. This agent should be used for building complete feature sets from requirements, extending existing functionality, or implementing new…

not rated 999 18d ago A 0 tokens

component-wrappers

438

bytechefhq/bytechef

Agent

How to build a ByteChef design-system component as a thin wrapper around a shadcn/ui primitive. Reference exemplars, already merged, live at.

not rated 998 yesterday A 0 tokens

android-expert

439

0xfurai/claude-code-subagents

Agent

Expert in Android development, specializing in modern Android practices, optimizing performance, and ensuring robust application architecture. Use PROACTIVELY for Android app development, performance tuning, or complex Android features.

not rated 995 +2 10mo ago A 42 tokens original MIT

researcher

440

jsmastery-pro/skills

Agent Claude Code

Read-only web and registry lookup. Use for Agent Skill / MCP discovery (npx skills find, MCP search), current-usage doc-checks, and scope source verification. Returns only a compact summary, never raw pages.

not rated 994 +21 26d ago A 48 tokens original MIT

review

441

AlmanacCode/codealmanac

Agent Claude Code

Architectural code reviewer for codealmanac. Use after meaningful code changes, before merging, or whenever code shape feels off.

not rated 993 +4 1mo ago A 28 tokens original Apache-2.0

instructions

442

activeagents/activeagent

Agent

System-level messages that guide agent behavior, personality, capabilities, and tool usage. The agent's operating manual for every interaction.

not rated 971 yesterday A 25 tokens original MIT

dev

443

piratuks/invoice-builder

Agent

Use this agent when implementing a feature, bug fix, or refactor in the Invoice Builder codebase.

not rated 978 yesterday A 23 tokens original MIT

ap-goal-checker

444

Spielewoy/autoprompt-skill

Agent

L4 terminal leaf - GOAL-CHECK. Independent, adversarial, default-FAIL. Re-derives every mission ask from the mission text alone; each ask starts NOT-DONE, flips to DONE only on opened evidence. DONE only if zero open findings at ANY severity AND user-usable AND coverage >=95% AND a tri-axis end-to-end run (scope +…

not rated 979 +17 5d ago A 92 tokens original MIT

gsd-executor

446

toonight/get-shit-done-for-antigravity

Agent Codex

Executes exactly one GSD PLAN.md with atomic per-task commits, deviation handling, and a SUMMARY.md artifact. Invoke once per plan so every plan execution starts from a clean context.

not rated 939 +5 15d ago A 42 tokens original MIT

microsoft/wassette

Agent ✓ vendor

Specialized agent for creating, updating, and maintaining Wassette project documentation using mdBook.

not rated 941 yesterday A 21 tokens original MIT

worker

449

rookie-ricardo/erduo-skills

Agent Claude Code

A stateless worker that completes one assigned task and returns a structured result. Stateless means it does not retain information between tasks.

not rated 934 1mo ago A 17 tokens original MIT

researcher

450

kdcokenny/ocx

Agent

Knowledge architect for external research and documentation.

not rated 939 +4 17d ago A 7 tokens original MIT

incident-investigator

451

ongridio/ongrid

Agent

An incident-investigation worker that follows a chain of causes back to the original source of a system alert or failure.

not rated 972 yesterday A 35 tokens AGPL-3.0

critic

452

JuliusBrussee/caveman-code

Agent

Adversarial review of a plan or implementation. Pokes holes; assumes the author was over-confident.

not rated 930 21d ago A 24 tokens original MIT

gpd-executor

453

psi-oss/get-physics-done

Agent

Default writable implementation agent for bounded GPD research execution. Handles PLAN.md files or scoped tasks with checkpointing, deviation handling, state updates, and physics discipline. Spawned by execute-phase, quick, and parameter-sweep workflows.

not rated 939 +5 1mo ago A 51 tokens

validate-module

454

Auties00/Cobalt

Agent Claude Code

Validates one WA module against its Cobalt counterpart(s) across static parity AND observable live-runtime parity by writing and executing a Java scratch file, then applies fixes.

not rated 916 +1 1mo ago A 36 tokens original MIT

analyzer

455

freestylefly/wesight

Agent

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

not rated 908 +3 11d ago A 0 tokens copy · 100% MIT

analyzer

456

luongnv89/asm

Agent

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

not rated 908 yesterday A 0 tokens copy · 100% 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: