claude

agent-runtime

Agent decision loop with human-approval gates, a seven-layer GuardChain preflight and a hash-chained action ledger.

278 on GitHubby nirholasv0.1.1Apache-2.0updated today

Not in a marketplace yet, so it loads for one session with --plugin-dir.

Plugin agent-runtime in nirholas/three.ws. Commands read from the repo's manifest — today.

What it installs

Skills (1)

  • guard-chain-preflight

    Preflight an agent tool call through the seven-layer GuardChain, run the plan/execute AgentRuntime loop with human approval, and verify a hash-chained action ledger using @three-ws/agent-runtime. Use when adding guardrails or an audit trail to an agent that can move funds.

View source on GitHub nirholas.github.io

More from nirholas/three.ws

All 76 plugins →

The three.ws skill pack: 3D model and avatar generation, building and monetizing agents on the platform, and the wallet/x402 agent economy.

49 skills

278

Give your coding agent free text-to-3D and rigged, animation-ready avatars. Works out of the box through the keyless three.ws Studio MCP server, with the paid mesh, avatar and auto-rig lanes, scene composition and live avatar embeds when you need them.

4 skills · 4 MCP servers

278

Pump.fun on-chain trading skills — create coins, swap tokens, manage creator fees, tokenize agents, and drive live avatar reactions from the pump.fun feed.

5 skills

278

Developer tools for three.ws: scaffold agents, configure MCP servers, and get runnable code examples for paid MCP tools.

3 commands · 1 MCP server

278

Read-only MCP server for three.ws trending agents and coins, the $THREE holder leaderboard and the activity ticker.

1 skill

278

agenc-mcp

claude

MCP server for the AgenC task marketplace and agent registry, with three.ws identity linking and x402 service discovery.

1 skill

278

Similar plugins

Human-verification gate for an agent loop: builds a single-file review page (the page itself makes no network request; a reviewed HTML artifact's own https: assets still load), collects batched feedback as structured batch.v1 data instead of chat prose, and refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed. Non-blocking, headless-guarded, round-capped. Stdlib-only.

1 skill · 1 command · 1 agent

alirezarezvani/claude-skills 29,725

Skills for building apps with the AG-UI .NET SDK: streaming chat (stateless vs hosted agents), server tools, client tools, human-in-the-loop (approvals & interrupts), shared state, multimodal messages, reasoning traces, protobuf transport, and troubleshooting.

9 skills

ag-ui-protocol/ag-ui 17,158

Turns the corrections and repeated workflows of your work sessions into small, reviewed skill updates: every change comes with its evidence and a written reason, and nothing touches a skill until you approve and install it.

1 skill

rebelytics/one-skill-to-rule-them-all 3,873

Ask real executives, operators and domain experts a question through Instant Expert and get a written or voice answer or a short call. It finds people by description or reaches a named person, and the user approves every live order. Starts in a free test mode with no account; you pay only if someone answers.

1 skill

davepoon/buildwithclaude 3,741

Build, evaluate, deploy, publish, and migrate Google ADK applications with Google's maintained agents-cli workflow for Agent Runtime, Cloud Run, GKE, and Gemini Enterprise.

1 skill · 1 command

jeremylongshore/tons-of-skills-marketplace 2,917

Correction-driven memory for coding agents: every correction becomes a fact, a test and a footprint commit in your repo. No API key, no database, no service.

7 skills

hashgraph-online/awesome-codex-plugins 1,566

Maintain agent-runtime?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins76 plugins