ClaudeMod
Back to browse
Agents

wshobson Agents

wshobson's production-tested agent definitions covering ML engineering, data pipelines, infrastructure automation, and API integration tasks.

wshobson35,996 starsAdded 3 months ago

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.

Claude Code Codex CLI Cursor OpenCode Gemini CLI

[!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

CountWhat it is
Plugins82Granular, single-purpose installable units (81 local + 1 external via git-subdir)
Agents191Domain experts (architecture, languages, infra, security, data, ML, docs, business, SEO)
Skills155Modular knowledge packages with progressive disclosure (load when activated)
Commands102Slash commands: scaffolding, security scans, test gen, infrastructure setup
Orchestrators16Multi-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:

TierModelUse
1Opus 4.7Architecture, security, code review, production-critical
2inheritUser-chosen — backend, frontend, AI/ML, specialized
3SonnetDocs, testing, debugging, API references
4HaikuFast operational tasks, SEO, deployment, content

→ Model configuration details

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):

HarnessGeneratesNotes
Claude Code(source-of-truth)Native marketplace.json + plugins/
Codex CLI.codex/skills/, .codex/agents/, AGENTS.md8 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 CLIskills/, 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:

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

Star History Chart

More Agents

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.

subagentsrolesqa+3
by VoltAgent
GitHub
Agents

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.

agentscommandsworkflow+2
by QD Henry
GitHub
Agents

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.

planningtask-breakdowntdd+2
by Affaan M
GitHub

Command Palette

Search for a command to run...