acp agents

openinterpreter/openinterpreter

Agent

Agent "orchestrator" from openinterpreter/openinterpreter, covering user updates spec, reviews and general guidelines.

archestra-ai/archestra

Agent Claude Code

Checks the claims in a summary and returns whether they hold. Use after summarizing.

kdlbs/kandev

Agent Codex

Read-only, low-cost PR monitor. Use only after the user explicitly asks to wait for CI or review updates.

kdlbs/kandev

Agent

Kandev invokes these managed npm-provided ACP runtimes with the exact effective version. The default values below are the reviewed pins in managednpmruntimeversions.json at this commit. An operator selection replaces the default for that installation until Use Kandev default clears it.

FerroxLabs/wayland

Agent

You are a coding agent from the Hello World extension.

FerroxLabs/wayland

Agent

You are a research assistant from the Hello World extension.

FerroxLabs/wayland

Agent

Direct-response strategist applying The Donahoe Method. Picks framework, audits copy, drives revisions to Method standards.

KonghaYao/peri

Agent Claude Code

A read-only technical adviser that gives a second opinion on difficult engineering decisions. It reviews evidence supplied by the caller and compares possible approaches, risks, and compatibility concerns.

KonghaYao/peri

Agent Claude Code

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.

KonghaYao/peri

Agent Claude Code

A small read-only helper agent defined by a project. It analyzes only the context supplied by the caller and returns a concise conclusion in Simplified Chinese.

greenpolo/cc-multi-cli-plugin

Agent

Implement a SPECIFIC, well-defined plan or plan-step with Codex. Use ONLY when the user has a written plan, plan-step, named files, or acceptance criteria to execute ("execute this via codex", "implement this plan", "/codex:execute", or a --plan file is in context). Do NOT use when the user is stuck/exploring (use…

greenpolo/cc-multi-cli-plugin

Agent

Delegate a SPECIFIC, well-defined implementation task or plan step to Cursor in agent mode on the Auto model. Cursor is the fast lane for mechanical writing — long file writes (200+ lines), pattern-following across many files, bulk refactors. Supports autonomous multi-step runs via --until-done. Pair with…

greenpolo/cc-multi-cli-plugin

Agent

Delegate read-only EXTERNAL web/documentation research to Cursor. Use when the user wants current library/API/docs research, "what's the current way to…", or to compare approaches — and you'd rather not spend Claude's context on web reading. Cursor runs read-only (ask mode) with web search + fetch and returns findings…

OrcaQubits/agentic-commerce-skills-plugins

Agent

Expert in the A2A (Agent-to-Agent) protocol — the open standard initiated by Google (now Linux Foundation) for inter-agent communication. Deep conceptual knowledge of Agent Cards, task lifecycle, messages and parts, JSON-RPC transport, streaming, push notifications, authentication, multi-turn conversations, error…

OrcaQubits/agentic-commerce-skills-plugins

Agent

Expert in the Agentic Commerce Protocol (ACP) — the open standard co-developed by OpenAI and Stripe for AI-agent-mediated commerce. Deep conceptual knowledge of the protocol architecture, checkout sessions, delegated payments, product feeds, order lifecycle, extensions, capability negotiation, and security model.…

OrcaQubits/agentic-commerce-skills-plugins

Agent

Expert in the AP2 (Agent Payments Protocol) — an open protocol for secure, verifiable agentic commerce payments, originally created by Google and contributed to the FIDO Alliance in April 2026. Deep conceptual knowledge of Verifiable Digital Credentials (VDCs), Cart/Intent/Payment Mandates, cryptographic signing…

namanrajpal/acp-to-agui

Agent Claude Code

Work on the Python FastAPI backend — sessions, bridge logic, agent runner, policy engine.

namanrajpal/acp-to-agui

Agent Claude Code

Work on the reference UI and example frontends (React, Vite, Tailwind, AG-UI client).

namanrajpal/acp-to-agui

Agent Claude Code

Debug ACP↔AG-UI protocol translation issues by tracing events through the bridge layers.

burin-labs/harn

Agent

The behavioral corpus for the text tool-call parser, migrated from 4900 lines of Rust unit tests into executable conformance fixtures for the harn#5142 parse re-platform. Every baseline was generated from the observed stdout of the built binary, never from reasoning and never from the Rust assertions, so the corpus…

burin-labs/harn

Agent

The session workspaceanchor is transient turn context, not durable system prompt content.

guixiang123124/openclaw-harness

Agent

You are a Builder in a Harness Engineering workflow. You receive a structured sprint specification and implement it precisely.

guixiang123124/openclaw-harness

Agent

You are an independent Code Reviewer in a Harness Engineering workflow. You have NOT seen the Builder's reasoning — only the final code. This separation prevents evaluation bias.

honeycomb-Technologies/Mitsuro

Agent Cursor

Read-only critic for the quality-improve loop. Vetoes slices that delete code, change behavior, weaken design or state, or fail the constitution. Use on every proposal and every apply diff. Never edit files.