skillsSource-backedReview first Safety ✓ Privacy ✓
wshobson Agentic Plugin Marketplace
Multi-harness agentic plugin marketplace with 84 plugins, 192 agents, 156 skills, 102 commands, and 16 orchestrators for Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot from one Markdown source tree.
HarnessClaude CodeCodexWindsurfGeminiCursorCLI
Level:expertType:capability-packVerified:validated
Review first — review before installing
Open the source and read safety notes before installing.
Safety notes
- This marketplace installs executable agent workflow instructions, slash commands, skills, and agent profiles. Review each selected plugin before giving it write, shell, network, MCP, cloud, browser, or deployment access.
- Some plugins target security scans, infrastructure, Kubernetes, cloud architecture, CI/CD, incident response, dependency management, and multi-agent orchestration; keep destructive, expensive, or production-impacting commands behind human approval.
- The marketplace includes external git-subdir plugin entries as well as local plugins. Verify external source repositories, manifests, licenses, update cadence, and dependency behavior separately.
- Cross-harness adapters intentionally transform source artifacts for Codex, Cursor, OpenCode, Gemini, and Copilot; inspect generated artifacts when relying on tool allowlists, model mappings, command conversion, or skill size limits.
- Do not assume every plugin is appropriate for every repository, compliance environment, model provider, or agent sandbox.
Privacy notes
- Installed plugins can expose project files, source code, issues, pull requests, logs, architecture notes, prompts, tool outputs, credentials accidentally present in context, cloud resource names, deployment details, and incident data to the configured agent runtime.
- MCP, memory, browser, cloud, and external plugin integrations may send prompts, file snippets, traces, or task context to additional local or remote services depending on configuration.
- Generated Codex, Cursor, OpenCode, Gemini, and Copilot artifacts may persist agent instructions, skills, commands, and project assumptions on disk.
- Keep secrets, customer data, regulated records, private infrastructure details, and unreleased business or incident material out of public plugin configs, examples, issues, PRs, screenshots, and generated docs.
Prerequisites
- Claude Code plugin marketplace support, Codex marketplace support, Cursor 2.5+ plugin support, OpenCode, Gemini CLI, GitHub Copilot, or a manual workflow that can consume the generated Markdown artifacts.
- Review of the target plugin manifest, agents, skills, commands, tools, external dependencies, and any generated harness-specific artifacts before installation.
- Node.js and npx for the documented Codex marketplace flow; git, make, and the target CLI for clone-and-generate Gemini or OpenCode workflows.
- A clear plugin scope, such as Python development, PR workflows, full-stack orchestration, security review, incident response, documentation, testing, or agent-team coordination.
- Project-level rules for file writes, shell commands, network access, MCP servers, credentials, cloud infrastructure, and long-running agent workflows.
Schema details
- Install type
- package
- Reading time
- 9 min
- Difficulty score
- 86
- Troubleshooting
- Yes
- Breaking changes
- No
Source repository stats
- Scope
- Source repo
Package metadata
Skill and platform metadata
- Skill type
- capability-pack
- Skill level
- expert
- Verification
- validated
- Verified at
- 2026-06-18
Retrieval sources
https://github.com/wshobson/agentshttps://raw.githubusercontent.com/wshobson/agents/main/README.mdhttps://raw.githubusercontent.com/wshobson/agents/main/docs/harnesses.mdhttps://raw.githubusercontent.com/wshobson/agents/main/docs/plugins.mdhttps://raw.githubusercontent.com/wshobson/agents/main/docs/agent-skills.mdhttps://raw.githubusercontent.com/wshobson/agents/main/.claude-plugin/marketplace.jsonhttps://raw.githubusercontent.com/wshobson/agents/main/plugins/python-development/.claude-plugin/plugin.jsonhttps://raw.githubusercontent.com/wshobson/agents/main/LICENSE
Tested platforms
Claude CodeCodexCursorOpenCodeGemini CLIGitHub CopilotAgent Skills compatible hosts
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
Tool listing metadata
- Website
- https://sethhobson.com
Full copyable content
# Claude Code
/plugin marketplace add wshobson/agents
/plugin install python-development
# Codex CLI
npx codex-marketplace add wshobson/agentsAbout this resource
wshobson Agentic Plugin Marketplace
wshobson/agents is an installable agentic plugin marketplace for Claude Code
and adjacent coding-agent harnesses. The repository README describes one
Markdown source tree that feeds Claude Code, Codex CLI, Cursor, OpenCode,
Gemini CLI, and GitHub Copilot artifacts.
Use this listing for the marketplace itself. Use narrower listings when reviewing a single plugin, one generated harness adapter, or a specific agent team inside the repository.
Knowledge Freshness
Repository metadata, source files, and marketplace docs were verified on 2026-06-18. The README lists 84 plugins, 192 agents, 156 skills, 102 commands, and 16 orchestrators. The committed Claude marketplace metadata reports version 1.7.1.
Claude Code plugin behavior, Codex marketplace support, Cursor plugin behavior, OpenCode configuration, Gemini CLI extension support, Copilot agent discovery, model aliases, skill-size limits, and MCP integration rules can change. Use the marketplace docs as the starting point, then verify the target harness docs and inspect the plugin you plan to install.
Retrieval Sources
This listing is grounded in:
- The upstream repository README.
- The cross-harness capability matrix in
docs/harnesses.md. - The plugin catalog in
docs/plugins.md. - The Agent Skills catalog in
docs/agent-skills.md. - The Claude plugin marketplace manifest.
- A representative
python-developmentplugin manifest. - The MIT license file.
- Current GitHub repository metadata.
Core Workflow
Claude Code users can register the marketplace and install individual plugins:
/plugin marketplace add wshobson/agents
/plugin install python-development
Codex users can add the committed Codex marketplace registry:
npx codex-marketplace add wshobson/agents
Gemini and OpenCode workflows use a clone-and-generate path:
gh repo clone wshobson/agents ~/agents
cd ~/agents
make generate HARNESS=gemini
gemini extensions install .
OpenCode users should follow the repository's make install-opencode flow,
which generates and symlinks OpenCode artifacts.
Capability Scope
The README and docs describe a broad marketplace:
| Area | Source-backed scope |
|---|---|
| Plugins | 84 installable units across development, docs, workflows, testing, security, data, operations, infrastructure, ML, and business categories |
| Agents | 192 domain experts for architecture, languages, infra, security, data, ML, docs, business, and SEO |
| Skills | 156 local Agent Skills across 41 plugins with progressive disclosure |
| Commands | 102 slash commands for scaffolding, security scans, tests, infrastructure, and workflows |
| Orchestrators | 16 multi-agent workflows for full-stack delivery, security, ML, and incident response |
| Evaluation | plugin-eval framework with static, LLM judge, and Monte Carlo evaluation modes |
The plugin catalog highlights common installs such as code-documentation,
debugging-toolkit, git-pr-workflows, backend-development,
frontend-mobile-development, full-stack-orchestration, unit-testing,
cloud-infrastructure, incident-response, python-development, and
javascript-typescript.
Multi-Harness Fit
The harness docs describe Claude Code as the source-of-truth implementation, with generated or committed support for other runtimes:
| Harness | Repository support |
|---|---|
| Claude Code | Native marketplace and plugin source under plugins/ |
| Codex CLI | Committed .agents/plugins/marketplace.json and per-plugin Codex manifests |
| Cursor | Committed .cursor-plugin/ and curated .cursor/rules/ |
| OpenCode | Generated .opencode/ agents, commands, skills, and config |
| Gemini CLI | Committed gemini-extension.json plus generated skills, agents, and commands |
| GitHub Copilot | Generated .copilot/ agents, skills, and commands |
This makes the repository useful for searches around "Claude Code plugin marketplace", "Codex plugin marketplace", "Codex CLI agent skills", "Gemini CLI agent skills", "OpenCode skills", and "multi-harness agent plugins".
Production Rules
- Install one plugin at a time and inspect its manifest, agents, commands, and skills before using it on sensitive code.
- Treat external plugin entries as separate supply-chain dependencies.
- Keep shell commands, MCP servers, browser access, cloud access, deployments, incident operations, and security scans behind explicit approval.
- Check generated artifacts before relying on cross-harness behavior such as tool allowlists, command conversion, model mapping, or skill truncation.
- Avoid loading the entire marketplace into context when a narrower plugin is enough.
- Pin and review updates in team environments rather than silently refreshing marketplace behavior across active projects.
Source Review
- The README describes the project as an "Agentic Plugin Marketplace" with 84 plugins, 192 agents, 156 skills, 102 commands, and 16 orchestrators.
- The README documents Claude Code marketplace installation with
/plugin marketplace add wshobson/agentsand a Codex path usingnpx codex-marketplace add wshobson/agents. docs/harnesses.mddocuments Claude Code, Codex, Cursor, OpenCode, Gemini, and Copilot support from a shared source tree.docs/plugins.mdlists 84 marketplace plugins, including development, documentation, workflow, testing, quality, utility, AI/ML, memory, data, database, operations, performance, and infrastructure categories.docs/agent-skills.mddocuments 156 local skills across 41 plugins and explains progressive disclosure..claude-plugin/marketplace.jsonidentifies the marketplace asclaude-code-workflowsand reports version 1.7.1.plugins/python-development/.claude-plugin/plugin.jsonis a representative local plugin manifest with MIT licensing.- The repository license is MIT.
Duplicate Check
No existing HeyClaude content entry was found for wshobson/agents, the
Agentic Plugin Marketplace, or a matching multi-harness agentic plugin
marketplace entry at the time this listing was created.
Disclosure
This is a community marketplace listing based on public source material. It is not a guarantee that every plugin, generated adapter, external dependency, or agent workflow is safe for a specific repository, organization, sandbox, model provider, compliance boundary, or production environment.
Source citations
Add this badge to your README
Show that wshobson Agentic Plugin Marketplace is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/skills/wshobson-agentic-plugin-marketplace)How it compares
wshobson Agentic Plugin Marketplace side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | wshobson Agentic Plugin Marketplace Multi-harness agentic plugin marketplace with 84 plugins, 192 agents, 156 skills, 102 commands, and 16 orchestrators for Claude Code, Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot from one Markdown source tree. Open dossier | Addy Osmani Agent Skills Addy Osmani's production-grade Agent Skills pack for AI coding agents, with lifecycle slash commands, engineering workflow skills, review personas, quality gates, and cross-agent setup guidance for Claude Code, Cursor, Gemini CLI, Antigravity CLI, OpenCode, GitHub Copilot, and other agents. Open dossier | Context Engineering Agent Skills MIT-licensed Agent Skills collection for context engineering, harness engineering, multi-agent architectures, filesystem context, memory systems, tool design, evaluation, hosted agents, and production agent operating loops for Claude Code, Cursor, Codex, and Open Plugins-compatible agent tools. Open dossier | Google Agents CLI Skills Google Agents CLI skill suite for coding agents that build, scaffold, evaluate, deploy, publish, and observe ADK agents on Gemini Enterprise Agent Platform, Agent Runtime, Cloud Run, GKE, and Google Cloud. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | skills | skills | skills | skills |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | Seth Hobson | Addy Osmani | Muratcan Koylan | |
| Added | 2026-06-18 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI |
| Source repo | — | — | — | — |
| Safety notes | ✓This marketplace installs executable agent workflow instructions, slash commands, skills, and agent profiles. Review each selected plugin before giving it write, shell, network, MCP, cloud, browser, or deployment access. Some plugins target security scans, infrastructure, Kubernetes, cloud architecture, CI/CD, incident response, dependency management, and multi-agent orchestration; keep destructive, expensive, or production-impacting commands behind human approval. The marketplace includes external git-subdir plugin entries as well as local plugins. Verify external source repositories, manifests, licenses, update cadence, and dependency behavior separately. Cross-harness adapters intentionally transform source artifacts for Codex, Cursor, OpenCode, Gemini, and Copilot; inspect generated artifacts when relying on tool allowlists, model mappings, command conversion, or skill size limits. Do not assume every plugin is appropriate for every repository, compliance environment, model provider, or agent sandbox. | ✓The slash commands are designed to guide real coding, testing, reviewing, committing, and shipping work; keep edits, commits, pushes, CI changes, and deploys behind the host's normal approval controls. `/build auto` is explicitly intended to generate a plan and implement multiple tasks in one approved pass. Use it on bounded specs, review the generated plan first, and stop on test failures or risky changes. The skills encode durable engineering workflows, not guaranteed-current framework APIs. Follow the source-driven-development guidance and verify current documentation before applying generated code. Security, CI/CD, observability, migration, and launch skills can touch production-sensitive systems. Require dry-run plans, rollback notes, and environment scoping before approving operational commands. Review personas and quality gates are useful second opinions, but they do not replace maintainer review, domain-specific tests, threat modeling, or release sign-off. | ✓These skills alter how agents select context, delegate work, persist state, design tools, evaluate outputs, and operate autonomous loops; use them as engineering guidance, not as automatic authority to change a production agent system. Filesystem-context and memory-system patterns can cause agents to write durable plans, scratchpads, logs, summaries, preferences, or shared handoff files. Keep cleanup, ownership, and review rules explicit. Harness-engineering, hosted-agent, and evaluation workflows can launch long-running loops, background agents, benchmark suites, paid model calls, or remote sandbox work. Require budgets, kill switches, rollback rules, and approval gates. Tool-design guidance can change MCP schemas, tool descriptions, return formats, and error contracts. Test routing and compatibility before deploying changes to users. Benchmark results are source evidence for this repository's claims, but they are workload-specific. Re-run or adapt benchmarks before relying on the reported routing numbers in a different agent stack. | ✓The skills intentionally guide agents through scaffold, eval, deploy, publish, CI/CD, infrastructure, datastore, and observability workflows that can create or modify cloud resources. Deployment and infrastructure commands may provision service accounts, IAM bindings, Terraform resources, Cloud Run services, Agent Runtime deployments, GKE resources, Artifact Registry images, Secret Manager entries, and CI/CD runners. The workflow skill explicitly requires clarifying goals and writing a spec before scaffolding a new project; skipping that step can create wrong infrastructure or unsafe agent behavior. Evaluation guidance may invoke LLM-as-judge, synthetic datasets, and prompt optimization; treat cost, data exposure, and nondeterminism as production concerns. Do not run deploy, publish, infrastructure, datastore, or CI/CD commands without explicit human approval and a known Google Cloud target. |
| Privacy notes | ✓Installed plugins can expose project files, source code, issues, pull requests, logs, architecture notes, prompts, tool outputs, credentials accidentally present in context, cloud resource names, deployment details, and incident data to the configured agent runtime. MCP, memory, browser, cloud, and external plugin integrations may send prompts, file snippets, traces, or task context to additional local or remote services depending on configuration. Generated Codex, Cursor, OpenCode, Gemini, and Copilot artifacts may persist agent instructions, skills, commands, and project assumptions on disk. Keep secrets, customer data, regulated records, private infrastructure details, and unreleased business or incident material out of public plugin configs, examples, issues, PRs, screenshots, and generated docs. | ✓Using the pack with an AI agent can expose repository code, product requirements, architecture notes, tests, CI logs, deployment settings, incidents, security findings, and launch plans to the configured model provider. Do not paste secrets, customer data, private incident records, production credentials, unpublished roadmap details, or proprietary compliance material into public prompts, issues, screenshots, or PR bodies. Agent personas and review workflows may ask for browser traces, performance data, logs, build output, dependency lists, and environment details; redact tokens and private URLs before sharing artifacts. | ✓Context-engineering work often touches prompts, system instructions, tool definitions, retrieved documents, message history, tool outputs, logs, scratch files, memory stores, benchmark prompts, and model responses. Do not persist secrets, customer data, private source code, incident data, unpublished strategy, or regulated records into scratchpads, skill examples, benchmark fixtures, or shared agent workspaces. If benchmark runners or hosted-agent examples call external models or remote sandboxes, review what prompts, traces, files, and logs are sent outside the local workspace. Agent memory and filesystem-context patterns should include deletion, redaction, retention, and access-control rules before being used with private projects. | ✓Agents CLI projects can contain Google Cloud credentials, AI Studio keys, Secret Manager names, service account emails, project IDs, regions, Terraform state, eval traces, prompts, tool outputs, logs, traces, user data, embeddings, and datastore contents. Eval artifacts and observability exports can include full prompts, tool calls, responses, failure rationales, trace IDs, and private application data. Publishing to Gemini Enterprise, deploying to Agent Runtime, Cloud Run, or GKE, and enabling analytics can move agent traffic into Google Cloud services subject to separate terms and access controls. Keep project IDs, credentials, Terraform state, traces, eval datasets, user data, private prompts, and secret names out of public issues, PRs, examples, and screenshots. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
More like this, weekly
A short, calm digest of reviewed Claude resources. Unsubscribe any time.