Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Handoff
MCP serversIT asset management — track equipment, allocations, and digital responsibility terms for your team.
-
Agent Handoff
MCP serversPass messages between AI agents with cleaning, metadata enrichment, and metered billing.
-
Handoff Watch
MCP serversSpots stalled agent-to-agent tasks and nudges or reassigns them. Works beside Offhand.
-
Secret Handoff
MCP serversLet agents use temporary secrets without receiving their values in chat. Local stdio; Node 22+.
https://github.com/geland/secrethandoff-integrations/releases/download/mcpb-v0.0.2/secrethandoff-multiplatform.mcpb -
claude-handoff
SkillsHand the current conversation off to a fresh background agent that picks up the work immediately.
-
ollama-handoff
MCP serversOffload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
ollama-handoff@0.1.2 -
Human Handoff relay
MCP serversHands CAPTCHAs, 2FA codes and approvals from your agent to your human with one tap.
-
brigade
SkillsBrigade Stack: run coding agents anywhere and keep one record of the work. Shared tasks, claims, verification receipts, handoffs, and MCP and skills sync for Claude Code, Codex, Cursor, OpenCode, and T3 Code.
git clone https://github.com/escoffier-labs/brigade.git -
handoff-desk
MCP serversHand tasks from Claude Code, Cursor or Codex to a personal agent through a folder of markdown notes.
@voyageurworks/handoff-desk@1.2.4 -
Dovri customer support handoff
MCP serversSearch published help and hand customer chat to a person. Requires your app's backend integration.
-
Followable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.
-
handoff — agent swarm coordination
MCP serversAgent swarm coordination: find funded work, form teams, run tasks, message E2E, get paid on verify.
-
You are a senior product designer and frontend architect. Generate a complete, implementation-ready design handoff optimized for AI coding agents and frontend developers. Be structured, precise, and system-oriented…
-
llm-tooling
SkillsAI-Tooling Sammelsurium
git clone https://github.com/Kalabint/llm-tooling.git -
Continuous-Claude-v3
SkillsContext management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
git clone https://github.com/parcadei/Continuous-Claude-v3.git -
Handoff: Send Files to Users & Agents
MCP serversSend a file to a user or agent as a share link with expiry, max opens, approval, revoke and logs.
-
aibadger
Tools & appsAI Badger - Local-first tool that extracts focused repo context for any AI chat (Claude, ChatGPT, Grok, etc.) without wasting tokens on irrelevant files.
git clone https://github.com/PVRLabs/aibadger.git -
repo-docs-skills
SkillsLiving project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as your repo evolves.
git clone https://github.com/YurunChen/repo-docs-skills.git -
figma-maxxing
Skills8 agent skills for real Figma files, for Claude Code, Codex, Copilot CLI and Gemini CLI: 90 Plugin API gotchas, checks before and after every write, a handoff gate.
git clone https://github.com/thiagoxikota/figma-maxxing.git -
whetstone
SkillsSmall, sharp, agent-agnostic skills that keep an AI agent's work honest.
git clone https://github.com/jovesun-lab/whetstone.git -
whatsnext
SkillsA shared plan, check-offs and resumable task progress for every coding agent in a project
git clone https://github.com/archid21/whatsnext.git -
ai-html-annotation
SkillsAgent Skill (html-prototype-build): generate, annotate, review & deliver native HTML prototypes for Claude Code, Cursor & Codex — real-DOM notes, AI-ready selectors, UI packs, multi-state screenshots.
git clone https://github.com/Lisuiwen/ai-html-annotation.git -
aispace
MCP serversSecure, expiring artifact storage and handoff for AI agents.
@aispace-sh/cli@0.4.1 -
Scout
MCP serversCoordinate local coding agents and track handoffs.
@openscout/scout@0.5.1
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.