Agents for Claude Code

47,676 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

gpd-executor

457

psi-oss/get-physics-done

Agent Claude Code

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 950 +30 1mo ago A 51 tokens

microsoft/wassette

Agent Claude Code ✓ vendor

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

not rated 941 3d ago A 21 tokens original MIT

gsd-executor

459

toonight/get-shit-done-for-antigravity

Agent Claude Code

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 +1 16d ago A 42 tokens original MIT

researcher

460

kdcokenny/ocx

Agent Claude Code

Knowledge architect for external research and documentation.

not rated 938 +5 18d ago A 7 tokens original MIT

worker

461

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

critic

462

JuliusBrussee/caveman-code

Agent Claude Code

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

not rated 931 +2 22d ago A 24 tokens original MIT

observer

463

hashgraph-online/awesome-codex-plugins

Agent Claude Code

Background agent that analyzes session observations to detect patterns and create instincts. Uses Haiku for cost-efficiency. v2.1 adds project-scoped instincts.

not rated 924 yesterday A 33 tokens original Apache-2.0

validate-module

464

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 918 +3 1mo ago A 36 tokens original MIT

analyzer

465

freestylefly/wesight

Agent Claude Code

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

not rated 911 +4 12d ago A 0 tokens copy · 100% MIT

analyzer

466

luongnv89/asm

Agent Claude Code

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

not rated 911 +3 yesterday A 0 tokens copy · 100% MIT

speckit.git.feature

467

snowdreamtech/frp

Agent Claude Code

Create a feature branch with sequential or timestamp numbering.

not rated 908 5d ago A 9 tokens original MIT

debugger

468

solatis/claude-config

Agent Claude Code

Analyzes bugs through systematic evidence gathering - use for complex debugging.

not rated 904 +3 5mo ago A 15 tokens original MIT

agent-creation

469

stencila/stencila

Agent Claude Code

Create a new Stencila agent. Use when asked to create, write, scaffold, or set up an agent directory or AGENT.md file. Covers workspace and user-level agents with model, provider, tool, trust, and MCP configuration.

not rated 903 +1 yesterday A 49 tokens original Apache-2.0

cnki-researcher

470

cookjohn/cnki-skills

Agent Claude Code

A research assistant for CNKI, a Chinese academic database. It helps search literature, find journals, and check whether journals are included in academic indexes.

not rated 895 +2 5mo ago A 49 tokens

seo-performance

471

Bhanunamikaze/Agentic-SEO-Skill

Agent Claude Code

Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.

not rated 890 +8 1mo ago A 18 tokens original MIT

drupal

472

ASCIT31/Dark-Moon

Agent Claude Code

Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Drupal applications (core, contrib modules, JSON:API, REST, Entity/Field system, Render API, Twig, Views, Drupal Commerce, roles/permissions).

not rated 890 +4 7d ago A 49 tokens GPL-3.0

sdk-reviewer

473

Azure/azure-sdk-for-rust

Agent Claude Code ✓ vendor

Azure SDK for Rust PR reviewer focused on API safety, guideline conformance, packaging, and release-readiness.

not rated 885 yesterday A 26 tokens original MIT

graduation

474

rush86999/atom

Agent Claude Code

The Agent Graduation Framework provides a rigorous, data-driven approach to promoting AI agents through maturity levels (STUDENT → INTERN → SUPERVISED → AUTONOMOUS). It uses episodic memory to track agent performance, validate constitutional compliance, and generate audit trails for governance requirements.

not rated 883 +1 changed 2d ago A 0 tokens AGPL-3.0

design-critic

475

plugin87/ux-ui-agent-skills

Agent Claude Code

Adversarial senior design critic. Renders the work, looks at it, and argues for rejection. Use when a build, screen, or component needs a taste and craft verdict that the automated gates cannot give. Runs after the gates are green, never instead of them.

not rated 879 +42 10d ago A 59 tokens

Agt. Builder

476

block/berd

Agent Claude Code ✓ vendor

Builds your agents with you, then keeps making them better.

not rated 873 +5 yesterday A 18 tokens original Apache-2.0

building-agents

477

promptise-com/Foundry

Agent Claude Code

Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.

not rated 869 16d ago A 0 tokens original Apache-2.0

analyzer

478

hAcKlyc/MyAgents

Agent Claude Code

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

not rated 867 +2 2d ago A 0 tokens AGPL-3.0

docs-drift-reviewer

479

ClickHouse/mcp-clickhouse

Agent Claude Code ✓ vendor

Checks whether README.md, server.json, fastmcp.json, and CHANGELOG.md still match the code on the current branch, and updates them where they do not. Use once implementation work is done, right before opening a PR, to catch drift in the environment variable tables, tool descriptions, response shapes, security…

not rated 866 yesterday A 75 tokens original Apache-2.0

CTO Agent

480

Salomondiei08/oh-my-hermes

Agent Claude Code

You move a product through Understand, Design, Build, Check, Ship, and Learn. You coordinate specialists, maintain focus, and communicate decisions to the founder. You own the whole product lifecycle, not only engineering. A pull request is evidence inside the build stage, not the goal.

not rated 857 1mo ago A 3 tokens

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: