Building agents

38,215 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

pstack-omp

1369

dsebban/skills

Skill Claude CodeCodex

OMP adapter for poteto-mode. Maps canonical pstack roles and lifecycle protocols to current OMP task agents, batching, isolation, IRC follow-ups, and durable result resources.

not rated 61 +3 27d ago A SkillSpector: pass 40 tokens original MIT

tkr-skill-writer

1370

tomkrikorian/visionOSAgents

Skill Codex needs its repo

Guide for creating and structuring skills with consistent formatting, clear documentation, and proper reference organization. Use when creating new skills or updating existing skill documentation.

not rated 61 2mo ago A 37 tokens original MIT

agent-ready

1372

dgalarza/claude-code-workflows

Plugin Claude Code

Bundles 1 skill · 100 tokens together

Make a codebase agent-ready with progressive-disclosure documentation, regression-aware quality gates, and opinionated, stack-specific project skill recommendations. Creates CLAUDE.md as a symlink for Claude Code compatibility.

not rated 60 changed 6d ago A tokens not measured original MIT

mind-clone

1373

yzfly/Mind-Cloning-Engineering

Skill Claude CodeCodex

Activate a Cognitive Digital Twin. Can simulate a custom subject (via core/ directory) OR load pre-installed celebrity/expert personas (from personas/ directory).

not rated 60 +1 8mo ago A 35 tokens original Apache-2.0

evolvent-ai/Terrarium

Skill Claude CodeCodex

Guide for writing Terrarium tasks. Use this skill when the user wants to create a new task.py, define checkers, use capabilities (email, calendar, workspace, postgres, notion, googlesheets), design multi-stage agent workflows, or integrate their own scenario into Terrarium. Activate whenever someone mentions writing…

not rated 60 +1 2mo ago A 90 tokens

Zaoqu-Liu/ScienceClaw

Skill Claude CodeCodex

Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology. Integrates tools from ToolUniverse's 1,264+ tool library, creates missing tools when needed using devtu-create-tool, tests thoroughly, and produces skills with Python SDK + MCP support. Use when asked to create new…

not rated 60 6mo ago A 90 tokens original MIT

moltbook

1377

SKYLENAGE-AI/QwenClawBench

Skill Claude CodeCodex

The social network for AI agents. Post, comment, upvote, and create communities.

not rated 60 3mo ago A 22 tokens original MIT

skill-vetter

1378

app-incubator-xyz/skill-vetter

Skill Claude Code

Multi-scanner security gate. TRIGGER when: user mentions installing, adding, or reviewing a skill to Claude Code, OpenClaw, or any other AI agent. Detects malicious code, vulnerabilities, and suspicious patterns.

not rated 60 6mo ago A 49 tokens

codex-cli

1379

nicepkg/vsync

MCP server Claude CodeCodexCursor +2

One of 2 in .mcp.json

MCP server wrapper for OpenAI Codex CLI. Runs locally from the codex-mcp-server npm package.

not rated 60 +1 7mo ago A tokens not measured original MIT

chief-agent

1380

thaitype/chief

Agent Claude Code

Goal-driven Planner/Orchestrator for the Chief Agent Framework. Reads AGENTS.md (highest priority), then .chief/rules, then milestone-specific goals. Produces and maintains milestone plans (plan/todo.md + task specs), delegates execution to builder-agent, delegates verification to tester-agent, and decides next…

not rated 60 +1 today A 155 tokens original MIT

Mindburn-Labs/helm-ai-kernel

Skill Claude CodeCodex

Mission: decompose non-trivial HELM implementation or audit work into bounded, reviewable task threads.

not rated 60 +5 yesterday A SkillSpector: pass 0 tokens original Apache-2.0

tokenwar

1382

oratelecom/tokenwar

Skill Claude CodeCodex

Activate, upgrade, test, and benchmark the 7-tool token-saving stack (context-mode, claude-mem, RTK, pxpipe, graphify, caveman, ponytail). Reports per-tool + per-provider (Codex, Gemini, Kimi, opencode, GitHub Copilot CLI) token savings, wires the stack into Copilot, and detects conflicts that would erase the gains.

not rated 60 changed 9d ago D 85 tokens original MIT

codex-tweaks/codex-tweaks

Skill Claude CodeCodex

Create or modify Codex Tweaks API v3 packages with lifecycle-safe Renderer code, optional fully trusted Node backends, typed UI extensions, package dependencies, priorities, and Git-installable metadata.

not rated 60 +4 2d ago A SkillSpector: warn 48 tokens original MIT

nightshift

1384

orwa-mahmoud/nightshift

Plugin Claude Code

Bundles 13 skills, 5 hooks · 226 tokens together

Keep long Claude Code runs on task: enforce the punch list, park questions, preserve progress, recover crashes, and run product or quality shifts until done.

not rated 60 +3 changed 4d ago A tokens not measured original MIT

codexmcp

1385

tomascupr/codexMCP

MCP server Claude CodeCodexCursor +2

Minimal FastMCP server that wraps the OpenAI Codex CLI. Runs locally from the codexmcp Python package.

not rated 60 1y ago A tokens not measured original MIT

parable

1386

Parcha-ai/parcha-skills

Plugin Claude Code

Bundles 1 skill, 1 plugin · 115 tokens together

Multi-model orchestration or explicit solo execution: route work across capable models, or run one exact proxy model with delegation disabled.

not rated 60 +1 today A tokens not measured original MIT

agtrace

1387

lanegrid/agtrace

MCP server Claude CodeCodexCursor +2

MCP server "agtrace" as configured in lanegrid/agtrace. Launched with agtrace serve.

not rated 59 +1 2mo ago A tokens not measured original Apache-2.0

coding-agent-harness

1388

FairladyZ625/coding-agent-harness

Skill Claude CodeCodex

A set of working methods for teams building long-running software projects with coding agents such as Codex or Claude Code. It covers project setup, planning, documentation, delivery, reviews, and automation.

not rated 59 2mo ago A 293 tokens AGPL-3.0

cache-audit

1389

ussumant/cache-audit

Skill Claude CodeCodex

Audit your Claude Code setup against prompt caching best practices. Checks ordering, tool stability, dynamic content handling, and hook injection patterns. Returns a scored report with specific fixes.

not rated 59 6mo ago A 38 tokens

clawdhub

1390

liteclaw/liteclaw

Skill Claude CodeCodex

Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.

not rated 59 7mo ago A 66 tokens original MIT

reskill-usage

1391

kanyun-inc/reskill

Skill Claude CodeCodex

Teaches AI agents how to use reskill — a Git-based package manager for AI agent skills. Covers CLI commands, install formats, configuration, publishing, and common workflows.

not rated 59 1mo ago A SkillSpector: warn 40 tokens original MIT

build-with-agent-team

1392

coleam00/agentic-chat-application-template

Skill Claude Code

Build a project using Claude Code Agent Teams with tmux split panes. Takes a plan document path and optional team size. Use when you want multiple agents collaborating on a build.

not rated 59 5mo ago A 0 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: