harness-skills
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…
Plugin bundle · by Ryan Alberts
About
harness-skills is a plugin bundle for AI coding tools published by Ryan Alberts. Marketplaces we read that list it: 1 (Community GitHub marketplaces). The last change we recorded was on 2026-10-21. As of our marketplace pass on 2026-10-21.
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 tool design, and a test drive of coding agents on tasks from your own git history.
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 ryanalberts/best-of-agent-harnesses
/plugin install harness-skills@agent-harnessesWhere it is published
| Marketplace | Status | Version | Figures | Verified | First seen |
|---|---|---|---|---|---|
| Community marketplace ryanalberts/best-of-agent-harnesses (Open the source on GitHub) | Listed | 1.0.0 | Forks (GitHub): 87 Stars (GitHub): 1 309 |
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) |
|---|---|---|
| agent-harnesses | ryanalberts/best-of-agent-harnesses | 1 309 |
How its figures have moved
- 2026-10-1681
- 2026-10-1782
- 2026-10-1885
- 2026-10-2187
- 2026-10-161.3k
- 2026-10-171.3k
- 2026-10-181.3k
- 2026-10-191.3k
- 2026-10-211.3k
Each dot is a day we read a different number; flat stretches are days the number did not move. Figures of different marketplaces are never added up.
What the bundle contains
As published on Community GitHub marketplaces.
Skills: 10
agents-md-checkerclaim-checkguardrail-testerharness-test-driveregression-finderrules-to-guardsrunaway-guardsandbox-checksession-waste-reporttool-design-checker
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.
-
Certifies any skill directory against the agentskills spec (level 2), hard platform limits from VS Code Copilot and the Codex loader (level 3), and non-blocking authoring…
-
Scaffold, build, verify, and share a new agent skill with the team.
-
For developers creating and maintaining skills for AI coding agents.
-
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
-
Reusable skills for AI coding agents. Every skill has a readable SKILL.md; 40 of 70 also carry a declarative protocol.yon with named steps, rules, and gates validated structurally…
-
Deterministic agent-plugin repository creation and maintenance workflows.
-
Public Builder skills for docs-first discipline, autonomous execution, cross-agent review, local-first Rewind memory, efficient agent workflows, clear status recaps, Agent-Native…
-
Static security audit toolkit for AI agent skills — surfaces every capability a skill may exercise, with evidence.
-
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.
-
Four-layer test framework for Claude Code plugin skills - structure validation, trigger accuracy, session testing, and skill value comparison
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)
-
A self-improving agent skill pipeline that prevents common AI coding agent failures. Includes 6 skills (plan-interview, intent-framed-agent, context-surfing, simplify-and-harden…
-
Health checker for Claude Code skills and commands. Scans ~/.claude/skills/ and commands/ for broken file references, deprecated MCP tool usage, missing frontmatter, script syntax…
-
Audits, diagnoses, and upgrades your Claude Code skills and agents
-
Skills to streamline adoption and usage of Giskard products (OSS, Hub, Guards) for testing, evaluating, and red-teaming AI agents.
-
Version tracking for Agent Skills bundles across sessions, surfaces, and platforms. When you load a skill into a new session, Skill Provenance reads the manifest, verifies file…
Has a listing on Claude Code: claude-plugins-official (5)
-
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to…
-
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.
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
Superpowers teaches Claude brainstorming, subagent driven development with built in code review, systematic debugging, and red/green TDD. Additionally, it teaches Claude how to…
-
Comprehensive development workflow for building AI agents with the Atomic Agents framework. Includes specialized agents for schema design, architecture planning, code review, and…
Has a listing on Claude: knowledge-work-plugins (5)
-
Official Buildkite skills for Claude Code, Cursor, and other AI coding agents — pipelines, migration, preflight, agent runtime, CLI, and API
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Bring Qodo's codebase intelligence, coding standards, and code review into your coding agent.
-
AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp
-
A suite of agent skills for the full GrowthBook feature flag and experimentation lifecycle.
Has a listing on Codex: openai-curated (openai/plugins) (5)
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
-
CrowdStrike Falcon Foundry development skills for building cybersecurity applications on the Falcon platform. Includes UI development, collections, functions, workflows, API…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Qodo setup, code intelligence, and review workflows.
Has a listing on Community GitHub marketplaces (5)
-
Certifies any skill directory against the agentskills spec (level 2), hard platform limits from VS Code Copilot and the Codex loader (level 3), and non-blocking authoring…
-
Scaffold, build, verify, and share a new agent skill with the team.
-
For developers creating and maintaining skills for AI coding agents.
-
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
-
Reusable skills for AI coding agents. Every skill has a readable SKILL.md; 40 of 70 also carry a declarative protocol.yon with named steps, rules, and gates validated structurally…
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…
-
Design, build, review, and publish GitHub Skills-style exercises with one coordinating agent and five Agent Skills for learner journeys, workflow-backed validation, and release…
-
Helps GitHub Copilot investigate mobile app telemetry, diagnose crashes, manage [bitdrift](bitdrift.ai) workflows and dashboards, integrate the Capture SDK into iOS, Android, and…
-
Meta prompts that help you discover and generate curated GitHub Copilot agents, instructions, prompts, and skills.
-
7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps.
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.
-
Advanced Security plugin for GitHub Copilot.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
-
Bring Azure DevOps work-item, repository, and pull-request workflows into GitHub Copilot.
-
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…
Has a listing on Cursor: cursor/plugins (5)
-
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.
-
CLI-backed repo compatibility scans plus agents that audit startup, validation, and docs against reality.
-
Patterns for designing CLIs that coding agents can run reliably: flags, help with examples, pipelines, errors, idempotency, dry-run.
-
Scaffold and validate new agent plugins.
-
Skills for building on the Cursor Origin API. Fetch the live spec first, then follow the Origin rules for credentials, scopes, webhooks, paging, and errors. Includes a skill that…
Has a listing on Docker MCP Catalog (5)
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Stop stitching context for Copilot and Cursor. With Sequa MCP, your AI tools know your entire codebase and docs out of the box.
-
MCP server for AI access to SmartBear tools, including BugSnag, Reflect, Swagger, PactFlow, QTM4J.
-
MCP server for terminal commands, file operations, and process management
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
Has a listing on Official MCP Registry (5)
-
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
-
Toolbox for AI agent skills: scaffold, lint, pack, install, and serve SKILL.md skills
-
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...
-
Find, inspect and install reviewed reusable AI-agent capabilities from superskill.sh.
-
skillmd com.skillmd/skillmd
Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.
Has a listing on npm registry (MCP servers) (5)
-
Discover and load Agent Skills from configured local directories and Git sources over stdio MCP.
-
One workspace for every AI coding assistant. Shared tasks, memory, and governance.
-
depwire io.github.atef-ataya/depwire
Dependency graph + 24 MCP tools. Impact analysis, simulation, security, agent coordination
-
Local persistent memory and Markdown wiki for AI coding agents: 24 MCP tools, no gateway required.
-
Read-only MCP server exposing the dsh-plugin-certification registry for DeepSeek Harness plugins.
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.