agent-harness
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task…
Pacote de plugins · de Alireza Rezvani
Resumo
agent-harness é um pacote de plugins para ferramentas de programação com IA publicado por Alireza Rezvani. Marketplaces que lemos e que o listam: 1 (Community GitHub marketplaces). A última mudança que registramos foi em 2026-10-15. Conforme nossa passagem pelos marketplaces em 2026-10-15.
Turn any domain folder of skills into a bounded agentic loop: a manifest builder inventories a domain's skills/tools/checks, a goal compiler turns a goal into a verifiable task plan (refusing vague goals with forcing questions), and a JSON-backed loop controller drives execute->verify->close with retry caps, controller-run verification (no verification theater), human escalation on exhausted budgets, and a close gate that refuses while any task is unverified or unwaived. Ships 3 stdlib Python tools, 18 committed per-domain harness manifests + JSON schema, 3 references citing the 2024-2026 agent-harness canon (Anthropic long-running harnesses, verifier's law, SWE-agent, Ralph loop, Cognition), harness-runner agent + /cs:harness command. Use when an agent or subagent should pick up a goal, define its tasks, complete and verify them, and close the loop.
O que pede
- Instala-se como pacote de plugins
Nenhum dos marketplaces que lemos publica as ferramentas ou as configurações que ele pede.
O que declara, pede e executa, por completo
Instale apenas plugins de desenvolvedores em quem você confia. Mostramos o que os marketplaces publicam e não testamos plugins.
Funciona com
- Claude Code
Pelos marketplaces que o listam e pelo transporte MCP que declara, conforme cada cliente documenta. Não testamos plugins.
Conectar
Comandos e configurações gerados apenas a partir do que os marketplaces declaram. Não os executamos por você e não testamos plugins.
Como plugin do Claude Code
Gerado a partir do que Community GitHub marketplaces declara.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install agent-harness@claude-code-skillsOnde está publicado
| Marketplace | Status | Versão | Números | Verificado | Visto pela primeira vez |
|---|---|---|---|---|---|
| Marketplace da comunidade alirezarezvani/claude-skills (Abrir o código no GitHub) | Listado | 1.0.0 | Forks (GitHub): 3 963 Estrelas (GitHub): 28 221 |
Sem marcação |
Cada número é do próprio marketplace e nunca é somado entre marketplaces. Um marketplace que não publica números não mostra nenhum: sem número não é zero.
Listado em um marketplace da comunidade
| Marketplace | Repositório | Estrelas (GitHub) |
|---|---|---|
| claude-code-skills | alirezarezvani/claude-skills | 28 221 |
O que o pacote contém
Conforme publicado em Community GitHub marketplaces.
Skills: 1
agent-harness
Comandos: 1
cs-harness
Agentes: 1
harness-runner
O que mudou
- Passou a ser um produto que acompanhamos
- Community GitHub marketplaces: apareceu
Plugins semelhantes
Produtos cujos próprios nomes, descrições, ferramentas e skills são os mais próximos deste pelo significado, em todos os marketplaces que lemos. A proximidade é ordenada apenas dentro desta lista.
-
Create production-grade agent skills that run in any harness — discoverable, behavior-driving, single-sourced, and validated.
-
Ten skills that test your agent harness on your own machine: sandbox reach, guardrails, 'tests pass' claims, rules the agent breaks, token waste, regressions after updates, MCP…
-
Design and scaffold self-running agent loops, plus a feedback-to-issue skill.
-
Harness leverages Claude Code's agent team system to decompose complex tasks into coordinated teams of specialized agents. Say "build a harness for this project" and it…
-
Build or run a reliable multi-agent task using the loop→chain→network→graph ladder.
-
HarnessKit is a professional-grade engineering framework that empowers AI agents with a robust 'harness' of structured controls and specialized personas. Built on the principles…
-
A judgment layer for building software with an agentic loop — eleven human-decision gates plus the loop-and-gate operating skill.
-
Loops (a file-based knowledge base) + a codebase harness (dev-local, e2e, crabbox cloud boxes, verify-before-ship) so agents can run, test, and ship code autonomously.
-
Scaffold, build, verify, and share a new agent skill with the team.
-
Spawn and manage autonomous background agents with persistent state across sessions
Plugins semelhantes por marketplace
A mesma pergunta feita a cada marketplace separadamente: existe lá um equivalente deste plugin?
Listado em Claude Code: claude-plugins-community (5)
-
Harness leverages Claude Code's agent team system to decompose complex tasks into coordinated teams of specialized agents. Say "build a harness for this project" and it…
-
HarnessKit is a professional-grade engineering framework that empowers AI agents with a robust 'harness' of structured controls and specialized personas. Built on the principles…
-
A judgment layer for building software with an agentic loop — eleven human-decision gates plus the loop-and-gate operating skill.
-
Spawn and manage autonomous background agents with persistent state across sessions
-
AI Agent Harness Engineering: bootstrap, audit, and evolve a reliable 6-layer agent harness for any project. Generates AGENTS.md, hooks (type-check, .env protection, auto-format…
Listado em Claude Code: claude-plugins-official (5)
-
Agentforce Agent Development Life Cycle — author, discover, scaffold, deploy, test, and optimize .agent files
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
-
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore, connecting tools, memory, policies, evaluation, debugging, and production…
Listado em Claude: knowledge-work-plugins (5)
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Skills, agents, and workflows for Honeycomb observability — query patterns, production investigations, SLOs, OpenTelemetry instrumentation, and Beeline migration. Designed to…
-
Work with incident.io from Claude: respond to and investigate incidents, check on-call schedules and escalations, and author the runbooks, skills and architecture docs that…
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
Listado em Codex: openai-curated (openai/plugins) (5)
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
Listado em Community GitHub marketplaces (5)
-
Create production-grade agent skills that run in any harness — discoverable, behavior-driving, single-sourced, and validated.
-
Ten skills that test your agent harness on your own machine: sandbox reach, guardrails, 'tests pass' claims, rules the agent breaks, token waste, regressions after updates, MCP…
-
Design and scaffold self-running agent loops, plus a feedback-to-issue skill.
-
Build or run a reliable multi-agent task using the loop→chain→network→graph ladder.
-
Loops (a file-based knowledge base) + a codebase harness (dev-local, e2e, crabbox cloud boxes, verify-before-ship) so agents can run, test, and ship code autonomously.
Listado em Copilot CLI: github/awesome-copilot (5)
-
Goal-driven task orchestration with independent verification. Interviews the user to define a clear goal, then loops between a Builder subagent (does the work) and an Inspector…
-
Three-agent workflow for orchestrated software delivery with an orchestrator plus implementation and QA subagents.
-
foundry-hosted-agent-copilotkit
Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native Foundry primitives, human-in-the-loop approvals, azd deploy, and…
-
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
Listado em Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
workiq-productivity
WorkIQ productivity skills powered by the local WorkIQ CLI — read-only insights across email, meetings, calendar, Teams, SharePoint, projects, and people.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
Listado em Cursor: cursor/plugins (5)
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Scaffold and validate new agent plugins.
Listado em Docker MCP Catalog (5)
-
Wayfound’s MCP server allows business users to govern, supervise, and improve AI Agents.
-
Documentation on AgentCore platform services.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Sequential Thinking (Reference)
Dynamic and reflective problem-solving through thought sequences.
-
Server-enforced workflow discipline for AI agents: work items, dependency graphs, quality gates
Listado em Official MCP Registry (5)
-
toolfactory io.github.GoatInAHat/toolfactory
Build an agent tool once; ship it as Agent Skills, MCP servers, Agent Plugins / Claude / Codex
-
Search, install and compose AI agent skills, loops and bundles from the LoopSkill marketplace.
-
skill-registry-sync io.github.dailyaiagents-cpu/skill-registry-sync
Auto-wire newly-shipped skills into owner-agent SOUL.md by reading `owner_agent:` frontmatter and...
-
tidebase io.github.BlueprintLabIO/tidebase
Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.
-
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
Encontrados pelo significado, não por código ou repositório em comum: plugins semelhantes continuam sendo produtos distintos, e isto não é uma avaliação nem uma recomendação.
Quer esta marca no seu plugin em nosso catálogo?
Prove que o mantém com um arquivo no repositório, um arquivo no seu domínio ou um registro DNS, e você poderá mostrar esta marca na ficha, com banners ao vivo para o seu site e o README. Como funciona a verificação
Você também recebe alertas quando um marketplace o publica, o remove, muda a marca de verificado ou o que ele pede, e o endpoint remoto passa a ser monitorado como um serviço web.
Dados de Community GitHub marketplaces. Os números vêm das nossas próprias passagens regulares pelos marketplaces, última leitura em . Não publicamos dados de contato dos editores de plugins.