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.

memory-mcp

1873

serkansmg/smg-claude-memory-mcp

MCP server Claude CodeCodexCursor +2

A python implementation of AI memory in MCP. Runs locally from the memory-mcp Python package.

not rated 33 +1 5mo ago A tokens not measured

graft

1874

chisomobanzi/Serpentine3D

MCP server Claude CodeCodexCursor +2

MCP server "graft" as configured in chisomobanzi/Serpentine3D. Launched with graft mcp.

not rated 33 +1 yesterday A tokens not measured copy · 100% MIT

graqle

1875

quantamixsol/graqle

Plugin Claude Code

Bundles 2 skills, 1 hook · 148 tokens together

GraQle dev intelligence layer: graph-powered codebase reasoning, impact analysis, and governed edits via MCP, plus governed-workflow skills and an optional governance gate hook.

not rated 32 1mo ago A tokens not measured

stone16/harness-engineering-skills

Plugin Claude Code

Bundles 2 skills, 5 agents · 208 tokens together

Two Claude Code engineering skills bundled as one plugin: review-loop (cross-LLM iterative code review with Codex or Gemini as peer) and harness (cybernetics-based Planner→Generator→Evaluator→Retro orchestration for complex tasks).

not rated 32 7d ago A tokens not measured original Apache-2.0

goal

1877

zebbern/agent-collab

Plugin Claude Code

Bundles 1 skill, 3 commands · 89 tokens together

Long-horizon project goals for Claude Code: an attended /goal loop that advances one increment at a time, delegating through the codex and cursor plugins.

not rated 32 29d ago A tokens not measured original Apache-2.0

agent-loop-skill

1878

dososo/agent-loop-skill

Cursor rule Cursor

Use for long-running, multi-step, verifiable, restartable AI agent tasks that need contracts, disk state, traces, role separation, subjective scoring, or cross-session continuity.

not rated 32 2mo ago A 36 tokens

author

1879

Ashkaan/contextium

Skill Claude Code needs its repo

Scaffold a conforming AI-layer artifact — a rule, skill, hook, agent, or output style — that already passes the format checks, then verify it. Use when adding any new AI-layer artifact — a shared one under .agents/ or a Claude-only one under .claude/ — so it matches the existing shape instead of drifting.

not rated 32 +1 changed 10d ago A SkillSpector: warn 72 tokens original MIT

ai-readme

1880

ZJunCher/ai-readme-skill

Skill Claude CodeCodex

A tool that scans a code project and creates guidance documents for both AI coding agents and human developers, including AGENTS.md and Cursor rule files.

not rated 32 4mo ago A 88 tokens

dr-ralph

1881

blencorp/dr-ralph

Plugin Claude Code

Bundles 3 commands, 1 hook · 20 tokens together

Implementation of the Dr. Ralph technique - continuous self-referential AI loops for interactive iterative development. Run Claude in a while-true loop with the same prompt until task completion.

not rated 32 8mo ago A tokens not measured

openclaw-docs

1882

tbdavid2019/openclaw-docs-skill

Skill Claude CodeCodex

Find authoritative guidance for installing, configuring, operating, securing, and troubleshooting OpenClaw, including channels, model providers, Gateway operations, tools, plugins, automation, nodes, multi-agent routing, and CLI errors. Use for any question or maintenance task involving an OpenClaw installation…

not rated 32 yesterday A 80 tokens AGPL-3.0

octo

1884

CES-Ltd/Lumi

Plugin Claude Code

Bundles 10 skills, 47 commands · 1,130 tokens together

v9.29.2 — Model defaults refreshed: Opus 4.7 for planning/strategy/security-review, GPT-5.4 for code-review/implementation. New GPT-5.4 prompting guide. Set OCTOPUSLEGACYROLES=1 to opt out. Run /octo:setup.

not rated 32 +1 4mo ago A tokens not measured original MIT

webmcp-kit

1885

nekuda-ai/webmcp-kit

Plugin Claude Code

Bundles 3 skills, 1 command, 2 hooks · 197 tokens together

Add WebMCP tools to a web app: read the repo, propose a reviewable tool plan, implement against @nekuda/webmcp-sdk, and verify the tools in a browser — or connect the tools a site already has, without rebuilding them.

not rated 32 +2 changed 10d ago A tokens not measured original MIT

quietloop

1886

zealxz/quietloop

Skill Claude CodeCodex

Use when designing or operating evidence-driven reflection, receipt-gated low-risk automation, privacy-preserving memory hygiene, or reliable notification recovery for Hermes-based personal agents. Do not use for generic journaling, unrestricted self-modification, or any workflow that cannot provide explicit approval…

not rated 32 +1 6d ago A 59 tokens original MIT

gum

1888

ehmo/gum

Skill Codex

Use when an agent needs Google API discovery, gum CLI calls, OAuth setup, or catalog-backed workflows.

not rated 32 7d ago A SkillSpector: pass 23 tokens original MIT

agent-discussion-panel

1889

JeremyDev87/codingbuddy

Skill Claude Code

Use when rendering a multi-agent discussion as a TUI panel. Defines terminal panel layout, component architecture, real-time streaming behavior, and integration points for displaying AgentOpinion data with bordered boxes, severity badges, and consensus indicators.

not rated 31 5mo ago A 50 tokens original MIT

text-optimize

1890

kochetkov-ma/claude-brewcode

Skill Codex

Optimizes text/docs for LLM token efficiency. Triggers - optimize, reduce tokens, compress, deep compress.

not rated 31 changed yesterday A 27 tokens

infinite-gratitude

1892

sstklen/infinite-gratitude

Skill Claude Code

Multi-agent research that keeps bringing gifts back — like cats! Dispatch multiple agents to research a topic in parallel, compile findings, and iterate on new discoveries.

not rated 31 6mo ago A 37 tokens original MIT

example-skill

1893

lukasz-fedor/claude-memory-template

Skill Claude Code

SKILL.md is the main instruction file for a skill. It's loaded into context when the user invokes this skill.

not rated 31 6mo ago C 0 tokens original MIT

agent-bom

1894

msaad00/agent-bom

Skill Codex

Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust across MCP discovery, CVEs, SBOMs, CIS benchmarks (AWS, Azure, GCP, Snowflake), OWASP/NIST/MITRE compliance, AISVS v1.0, MAESTRO layer tagging, and vector database security checks. Use when the user mentions…

not rated 31 changed today A SkillSpector: warn 107 tokens original Apache-2.0

scalvert/docusaurus-plugin-mcp-server

Skill Claude CodeCodex

Expose a Docusaurus site's docs as an MCP server for AI agents — add the build-time plugin, deploy the MCP endpoint to any web-standard serverless/edge runtime, run it locally, or add the install button. Load when working with docusaurus-plugin-mcp-server or its /adapters or /theme entry points.

not rated 31 1mo ago A SkillSpector: pass 75 tokens original MIT

FutureAtoms/agentic-control-framework

MCP server Claude CodeCodexCursor +2

MCP-compliant agentic control framework with 83+ tools for Claude Code and autonomous agent development. Runs locally from the agentic-control-framework npm package.

not rated 31 11mo ago A tokens not measured

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: