Building agents

38,442 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.

concilium

5282

raichominev/concilium

Plugin Claude Code

Bundles 1 skill, 3 commands · 548 tokens together

Cross-model adversarial review and idea generation. A Claude session orchestrates and ratifies; OpenAI (codex), Moonshot (kimi) and xAI (grok) seats probe, replicate and generate — all on subscription auth, no API key required. Ten modes: review, forge, instrument audit, fragment verify, blind replication, and more.

not rated 2 changed today A tokens not measured original Apache-2.0

abs

5283

Ra-Pay-AI/abs-skill

Skill Claude CodeCodex

The CLI of the AI Agent Economy. The first CLI social network and marketplace for AI agents. Humans are in the loop for claiming agents (GitHub OAuth), approving purchases, and completing seller onboarding.

not rated 2 3mo ago A 42 tokens

Aidress-ai/aidress-skill-find-verified-data-enrichment-agent

Skill Claude CodeCodex

Find a Verified Data Enrichment Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for data agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 63 tokens original MIT

Aidress-ai/aidress-skill-find-verified-data-extraction-agent

Skill Claude CodeCodex

Find a Verified Data Extraction Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for data agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 62 tokens copy · 88% MIT

instincts

5286

Fergius-Engineering/instincts

Plugin Claude Code

Bundles 20 skills, 2 hooks · 602 tokens together

The reflex layer on top of superpowers. Tunes an agent's working instincts — verify against the source, instrument for remote diagnosis, write for humans, test with teeth.

not rated 2 25d ago A tokens not measured original MIT

Self-Improvement Loop

5287

ralfyishere/rules-with-receipts

Skill Claude Code

Learn from prior mistakes and repeated patterns - review what failed, extract a reusable lesson, apply it to the next attempt. Activate when the user corrects your output, when an approach fails and needs a retry, when you notice the same friction recurring across tasks, and at the end of significant multi-step work.…

not rated 2 2mo ago A 111 tokens original MIT

0fuk/OpenACCP

Skill Claude CodeCodex

Run delegated-final-authority OpenACCP coordination. Use for coordination decisions, authority charters, dispatch, final handoff consume, PR/CI/merge readiness, publication readiness, owner-ready waiver recommendations, and accepting or rejecting reviewed evidence when delegated by charter.

not rated 2 1mo ago A 60 tokens original MIT

delegate

5291

triumsebas/unlimited-mcp

Skill Claude CodeCodex

Opinionated, Claude-Code-specific patterns on top of the unlimited-mcp MCP tools. Requires the unlimited-mcp server to be connected.

not rated 2 3mo ago A 0 tokens original Apache-2.0

Aidress-ai/aidress-skill-find-verified-freight-booking-agent

Skill Claude CodeCodex

Find a Verified Freight Booking Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for logistics agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

not rated 2 2mo ago A 64 tokens original MIT

agent-discussion

5295

leviuszen/meaning-assurance

Skill Claude CodeCodex

Use when Codex needs read-only external feedback for planning, architecture review, code discussion, strategy review, or decision support.

not rated 2 1mo ago A 29 tokens original Apache-2.0

skill-version-manager

5296

Cifferni/skill-version-manager

Skill Claude CodeCodex

Local version management for installed skills. Provides version archiving, history viewing, and rollback capabilities. Use when you need to manage local skill versions, revert changes, or save snapshots of modified skills.

not rated 2 1mo ago A 43 tokens

switch-api

5298

JarlZhang/claude-presets

Skill Claude CodeCodex

A project configuration tool for switching Claude Code between saved API connections or back to a Claude subscription account. An API connection is a service and set of credentials that lets software use a model.

not rated 2 1mo ago A 234 tokens original MIT

self-evolving-agent

5299

SELAT-AI/selat-skills

Skill Claude CodeCodex

Use this skill when the user wants to design or operate a budgeted economic agent with its own operational identity, AgentMail address, agent-wallet treasury, infrastructure budget, social and financial intelligence loop, monetization or trading hypotheses, and reinvestment policy. The skill enforces treasury…

not rated 2 today A 89 tokens original Apache-2.0

minicode_usage

5300

WalterSumbon/minicode-sdk

Skill Claude CodeCodex

Guide for using the minicode-sdk library. Use this skill when the user wants to learn how to use minicode-sdk to build AI agents, integrate tools, use MCP servers, or configure the SDK.

not rated 2 7mo ago A 45 tokens original MIT

claude-api

5301

lk19940215/claude-coder

Skill Claude CodeCodex

Use this skill when the user is building against Anthropic APIs or SDKs, including @anthropic-ai/sdk, anthropic, or Agent SDK integrations.

not rated 2 5mo ago A 0 tokens

codepatchbay

5302

changw98ic/codepatchbay

Skill Codex

Use CodePatchBay, the published npm package and cpb CLI for local-first verified AI coding workflows. Trigger when the user asks to install or run CodePatchBay/CPB, route a coding task through plan -> execute -> verify, inspect CPB artifacts or verdicts, set up CPB agents, run CPB demo/doctor/status/retry/cancel, or…

not rated 2 1mo ago A 92 tokens AGPL-3.0

usewire/wire-plugins

Plugin Claude Code

Official Claude Code plugins from Wire — persistent memory, context management, and AI agent tools.

not rated 2 4mo 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: