wshobson Agents
wshobson's production-tested agent definitions covering ML engineering, data pipelines, infrastructure automation, and API integration tasks.
Agentic Plugin Marketplace
Production-ready agentic workflow building blocks: 82 plugins, 191 agents, 155 skills, 102 commands — built for Claude Code and consumed natively by OpenAI Codex CLI, Cursor, OpenCode, and Gemini CLI from a single Markdown source.
[!NOTE] One source-of-truth (
plugins/), five harnesses. Each harness gets idiomatic, harness-native artifacts — not lowest-common-denominator translations. See docs/harnesses.md for the capability matrix.
Quick start
Pick your harness:
Claude Code
/plugin marketplace add wshobson/agents
/plugin install python-development # or any of 82 plugins
→ Full Claude Code setup, troubleshooting, and plugin catalog
Codex CLI · Cursor · OpenCode · Gemini CLI
gh repo clone wshobson/agents ~/agents
cd ~/agents
make generate HARNESS=<codex|cursor|opencode|gemini>
Setup details and per-harness gotchas: docs/harnesses.md. Gemini-specific setup: GEMINI.md (also auto-loaded by Gemini CLI).
What's inside
| Count | What it is | |
|---|---|---|
| Plugins | 82 | Granular, single-purpose installable units (81 local + 1 external via git-subdir) |
| Agents | 191 | Domain experts (architecture, languages, infra, security, data, ML, docs, business, SEO) |
| Skills | 155 | Modular knowledge packages with progressive disclosure (load when activated) |
| Commands | 102 | Slash commands: scaffolding, security scans, test gen, infrastructure setup |
| Orchestrators | 16 | Multi-agent coordination workflows (full-stack, security, ML, incident response) |
Browse the catalog: docs/plugins.md · docs/agents.md · docs/agent-skills.md
How it works
Each plugin is isolated and composable: agents, commands, and skills are auto-discovered from directory structure. Installing a plugin loads only its components into context — not the whole marketplace.
plugins/python-development/
├── .claude-plugin/plugin.json
├── agents/ # 3 Python agents (python-pro, django-pro, fastapi-pro)
├── commands/ # 1 scaffolding command
└── skills/ # 16 specialized skills (async, testing, packaging, …)
Three-tier model strategy:
| Tier | Model | Use |
|---|---|---|
| 1 | Opus 4.7 | Architecture, security, code review, production-critical |
| 2 | inherit | User-chosen — backend, frontend, AI/ML, specialized |
| 3 | Sonnet | Docs, testing, debugging, API references |
| 4 | Haiku | Fast operational tasks, SEO, deployment, content |
Multi-harness support
This marketplace ships to five agentic harnesses from one Markdown source. Each adapter emits harness-native artifacts (not lowest-common-denominator translations):
| Harness | Generates | Notes |
|---|---|---|
| Claude Code | (source-of-truth) | Native marketplace.json + plugins/ |
| Codex CLI | .codex/skills/, .codex/agents/, AGENTS.md | 8 KB skill cap respected; commands → skills |
| Cursor | .cursor-plugin/, .cursor/rules/ | Thin marketplace + curated rules; reuses .claude/ |
| OpenCode | .opencode/agents/, .opencode/commands/ | permission: block from tools: allowlist |
| Gemini CLI | skills/, agents/, commands/ (TOML) | Native skills + subagents (April 2026 spec) |
make generate-all # all four
make validate # structural checks
make garden # drift / dead-link / cap detection
→ Full capability matrix and per-harness deep-dives
Quality evaluation
plugin-eval is a three-layer evaluation framework for measuring
and certifying plugin/skill quality:
- Static — deterministic structural analysis (<2s, free)
- LLM Judge — semantic evaluation across 4 dimensions (~30s, Haiku + Sonnet)
- Monte Carlo — statistical reliability via 50-100 simulated runs (~2-5 min)
uv run plugin-eval score path/to/skill --depth quick
uv run plugin-eval certify path/to/skill
→ PluginEval framework documentation
Documentation map
Detail lives in docs/. Read in this order:
- docs/plugins.md — full catalog of all 82 plugins
- docs/agents.md — all 191 agents by category
- docs/agent-skills.md — 155 skills with progressive disclosure
- docs/usage.md — commands, workflows, examples
- docs/architecture.md — design principles
- docs/harnesses.md — cross-harness capability matrix
- docs/authoring.md — portable-content style guide
- docs/plugin-eval.md — quality evaluation framework
- docs/round-trip-results.md — real-CLI verification recipes
Gemini-specific setup: GEMINI.md. All other harness setup, capability deltas, and gotchas live in docs/harnesses.md.
Contributing: CONTRIBUTING.md · Authoring: docs/authoring.md
Related plugins (external sources)
-
Pensyve — universal memory runtime with cross-session cognitive memory for Claude Code.
/plugin marketplace add major7apps/pensyve /plugin install pensyve@major7apps-pensyve
License
MIT — see LICENSE.
Star history
More Agents
Awesome Claude Code Subagents
VoltAgent's curated collection of Claude Code subagent definitions — specialized roles for QA, security, DevOps, architecture review, and code generation.
Claude Command Suite
qdhenry's all-in-one agent + command collection — pre-built sub-agents paired with slash commands for a complete Claude Code workflow out of the box.
ECC Planner Agent
Feature implementation planning agent from everything-claude-code — breaks down requirements into ordered tasks with TDD anchors, dependency graph, and acceptance criteria.