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.

backchannel

5618

unison-labs-ai/backchannel

Skill Claude CodeCodex

Use when coordinating with other AI agents via backchannel (bch) — checking the inbox at task start, sending DMs or channel messages to peer agents, requesting reviews, or reacting to incoming messages. Trigger phrases include "message the other agent", "check your inbox", "tell codex/claude/gemini to…", or any task…

not rated 2 3mo ago A 83 tokens original MIT

delegate

5619

kanoniv/auth-action

Skill Claude Code

Cryptographic delegation for AI agents. Scope-confines what Claude Code can do in this session using Ed25519 delegation tokens. Every action is verified before execution and signed for the audit trail. Use when asked to "delegate", "restrict scope", "authorize", or "sudo mode".

not rated 2 5mo ago A 61 tokens

dead-letter

5620

Wh0FF24/whoff-agents

Skill Claude CodeCodex

Capture a failed or blocked task before it disappears. Categorizes the failure mode, extracts what was learned, and generates either a retry packet with the root cause fixed or an escalation message with specific decision points. Use whenever an agent returns a blocker, error, or partial result.

not rated 2 2mo ago A 58 tokens original MIT

claude-code-migration

5621

rushengzhou/sid-code

Skill Claude Code

A guided tool for copying Claude Code settings and project configuration into sid-code. It checks what can be moved, asks before writing, and records what was transferred.

not rated 2 19d ago A 100 tokens original MIT

assets

5622

foritin/r-code

Skill Claude CodeCodex

R-Code can be available as a local MCP server named r-code. Use it only when the user asks you to delegate a focused investigation to R-Code's own Agent.

not rated 2 4d ago A 0 tokens original MIT

kimi-partner

5623

jevonhou/kimi-partner

Skill Claude CodeCodex

Delegate an explicitly approved local coding task from Codex to Kimi Code, monitor it, return review feedback to the same Kimi session, and independently verify the result. Use only when the user explicitly asks to try Kimi or has approved a Codex suggestion to use Kimi for the current task.

not rated 2 2mo ago A 65 tokens original MIT

using-agentic-mcp

5625

F0rty-Tw0/agentic-mcp

Skill Claude CodeCodex

Use when an AI agent needs a repeatable workflow to get a real answer or compare providers through agentic-mcp, with discovery, proof, and CLI fallback steps.

not rated 2 3mo ago A 40 tokens original MIT

extension-foundry

5626

sdfdu/evopilot

Skill Claude CodeCodex

Analyze repeated EvoPilot observations and compile proven workflows into portable, versioned Agent Skills or other reviewed extensions. Use when improving or extending the agent itself.

not rated 2 changed 14d ago A 34 tokens original MIT

vault-mcp-dev

5627

videnovnebojsa/vault-mcp

MCP server Claude CodeCodexCursor +2

MCP server "vault-mcp-dev", hosted remotely at 127.0.0.1, as configured in videnovnebojsa/vault-mcp.

not rated 2 13d ago A tokens not measured original MIT

codex-channels

5629

cafitac/codex-channels

Skill Claude CodeCodex

Skill "codex-channels" from cafitac/codex-channels, covering codex-channels, execution-first rule, fastest shortcuts, codex operator mode and fastest operator check.

not rated 2 4mo ago A 30 tokens original MIT

ai-change-impact

5630

starbringer/AI-Insights

Skill Claude Code

Measure what a change to an AI coding setup actually saved, in dollars. Compares recorded before/after usage from the AI Insights MCP server — either two specific sessions by id, or everything in one period against another — and attributes the cost difference to the factor that moved it: fewer API calls, less context…

not rated 2 1mo ago A 169 tokens original MIT

koshi

5631

jsharma1105/Koshi

Plugin Claude Code

Bundles 5 agents · 340 tokens together

Koshi MCP — retrieval, context engineering, persistent memory, and quality scoring for AI agents. 100% offline.

not rated 2 28d ago A tokens not measured original MIT

intelligent-routing

5632

ashrafmusa/agenticana

Skill Claude CodeCodex

Automatic agent selection and intelligent task routing. Analyzes user requests and automatically selects the best specialist agent(s) without requiring explicit user mentions.

not rated 2 5d ago A 32 tokens original MIT

new-skill

5633

zjshen14/opencli

Skill Claude Code

Scaffold a new custom SKILL.md file interactively. Use when asked to create a new skill or slash command.

not rated 2 26d ago A 28 tokens original MIT

ferry

5634

PunkGo/ferry

Skill Claude CodeCodex

Delegate bounded coding work to a Codex worker, including an explicitly configured alternate model/provider through the official Codex SDK and App Server, or diagnose worker readiness. Use when the user asks to delegate, use a worker/custom model/provider, steer or interrupt delegated work, or run Ferry doctor. Do not…

not rated 2 26d ago A 75 tokens original MIT

a2amesh

5636

oaslananka/a2amesh

Plugin Claude Code

Bundles 3 skills, 1 MCP server · 93 tokens together

A2A Mesh workflows for endpoint validation, approved task operations, and security-bounded MCP consumption.

not rated 2 yesterday A tokens not measured original Apache-2.0

mcp-docs

5637

pusewicz/cf-mcp

MCP server Claude CodeCodexCursor +2

The MCP documentation itself, served as an MCP server: lets the agent search the protocol spec and guides. Remote server at modelcontextprotocol.io.

not rated 2 today A tokens not measured copy · 100% MIT

tonytanglab/deepseek-harness-relay-mcp

Skill Codex

Dispatch and monitor an explicitly scoped, simple or medium-complexity local subtask through models available in DeepSeek Harness, including read-only review and user-authorized workspace implementation. Use when the user says “调用 Harness”, asks Harness to analyze or review, or delegates a fix, edit, refactor, test…

not rated 2 changed 4d ago A 94 tokens original MIT

turtle

5639

contactandrewchl-wq/turtle-mcp

Plugin Claude Code

Bundles 26 skills · 1,660 tokens together

Memoria persistente y coordinación multi-agente para agentes de IA, eficiente en tokens.

not rated 2 2mo ago A tokens not measured original MIT

goal-orchestrator

5640

Eyalm321/hyperpanes

Skill Claude Code

Run a long-lived, headless per-project GOAL orchestrator on hyperpanes — hold a project's goal list, spawn a fable/opus spec agent per goal, have it fan work out to sonnet impl agents via the durable work queue, watchdog wedged agents, rotate across Claude accounts on limits, and loop 24/7. Use when the user wants a…

not rated 2 yesterday A 117 tokens original 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: