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…
Plugin bundle · by Alireza Rezvani
About
agent-harness is a plugin bundle for AI coding tools published by Alireza Rezvani. Marketplaces we read that list it: 1 (Community GitHub marketplaces). The last change we recorded was on 2026-10-15. As of our marketplace pass on 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.
What it asks for
- Installs as a plugin bundle
None of the marketplaces we read publishes its tools or the settings it asks for.
What it declares, asks for and runs, in full
Only install plugins from developers you trust. We list what marketplaces publish and do not test plugins.
Works with
- Claude Code
From the marketplaces that list it and the MCP transport it declares, as each client documents them. We do not test plugins.
Connect
Commands and configs built only from what its marketplaces declare. We do not run them for you and do not test plugins.
As a Claude Code plugin
Built from what Community GitHub marketplaces declares.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install agent-harness@claude-code-skillsWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Community marketplace alirezarezvani/claude-skills (Open the source on GitHub) | Listed | 1.0.0 | Forks (GitHub): 3 963 Stars (GitHub): 28 221 |
Not marked |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
Listed in one community marketplace
| Marketplace | Repository | Stars (GitHub) |
|---|---|---|
| claude-code-skills | alirezarezvani/claude-skills | 28 221 |
What the bundle contains
As published on Community GitHub marketplaces.
Skills: 1
agent-harness
Commands: 1
cs-harness
Agents: 1
harness-runner
What changed
- Became a product we track
- Community GitHub marketplaces: appeared
Similar plugins
Products whose own names, descriptions, tools and skills are closest in meaning to this one, on every marketplace we read. Closeness is ranked within this list only.
-
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
Similar plugins by marketplace
The same question asked of one marketplace at a time: is there an analog of this plugin there?
Has a listing on 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…
Has a listing on 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…
Has a listing on 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…
Has a listing on 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.
Has a listing on 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.
Has a listing on 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.
Has a listing on 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.
Has a listing on 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.
Has a listing on 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
Has a listing on 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.
Found by meaning, not by shared code or a shared repository: similar plugins stay separate products, and this is not a review or a recommendation.
Want this mark on your plugin in our catalog?
Prove you maintain it with a file in its repository, a file on your domain or a DNS record, and you can show this mark on the card, with live banners for your site and README. How verification works
You also get alerts when a marketplace lists it, drops it, changes its verified mark or what it asks for, and its remote endpoint goes on monitoring as a web service.
Data comes from public marketplace files in GitHub repositories of their authors. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.