Loading plugin...

wshobson-agents · Flowy

README

Agentic Plugin Marketplace

Production-ready agentic workflow building blocks: 94 plugins, 203 agents, 175 skills, 109 commands — built for Claude Code and consumed natively by OpenAI Codex CLI, Cursor, OpenCode, Gemini CLI, and GitHub Copilot 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 94 plugins

→ Full Claude Code setup, troubleshooting, and plugin catalog

Codex CLI · Cursor · OpenCode · Gemini CLI · Copilot

Codex and Cursor install natively from the committed registries (which point at the source plugins/):

npx codex-marketplace add wshobson/agents        # Codex; then install individual plugins
# Cursor: add the marketplace, then `/plugin install <name>` (reads .cursor-plugin/ + source)

Gemini and OpenCode install via clone + generate (the transformed trees are gitignored):

gh repo clone wshobson/agents ~/agents && cd ~/agents
make generate HARNESS=gemini && gemini extensions install .   # Gemini
make install-opencode                                          # OpenCode (runs generate + symlinks)

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	94	Granular, single-purpose installable units (90 local + 4 external via git-subdir)
Agents	203	Domain experts (architecture, languages, infra, security, data, ML, docs, business, SEO)
Skills	175	Modular knowledge packages with progressive disclosure (load when activated)
Commands	109	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, …)

Tiered model strategy:

Tier	Model	Use
0	Fable 5	Longest-horizon autonomous work — large migrations, multi-hour runs (opt-in, premium cost)
1	Opus	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

→ 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):

Harness	Generates	Notes
Claude Code	(source-of-truth)	Native `marketplace.json` + `plugins/`
Codex CLI	`.agents/plugins/marketplace.json` + `plugins/*/.codex-plugin/plugin.json` (committed); `.codex/skills/`, `.codex/agents/` (gitignored)	8 KB skill cap respected; commands → skills
Cursor	`.cursor-plugin/`, `.cursor/rules/`	Thin marketplace + curated rules; reuses `.claude/`
OpenCode	`.opencode/agents/`, `.opencode/commands/`, `.opencode/skills/`	`permission:` block from `tools:` allowlist; OpenCode-safe skill names
Gemini CLI	`skills/`, `agents/`, `commands/` (TOML)	Native skills + subagents (April 2026 spec)
Copilot	`.copilot/agents/`, `.copilot/skills/`, `.copilot/commands/`	Markdown agent profiles + SKILL.md skills + commands-as-skills; model maps to native Claude models

make generate-all                        # all five
make validate                            # structural checks
make garden                              # drift / dead-link / cap detection

Codex and Cursor install from source via committed registries; Gemini and OpenCode install via clone + make.

→ 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 94 plugins
docs/agents.md — all 203 agents by category
docs/agent-skills.md — 175 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

External Memory Integration

Pensyve is included as an external git-subdir entry for Claude Code. Pensyve also maintains direct upstream integrations for this marketplace's other supported harnesses.

Harness	Pensyve integration
Claude Code	`/plugin install pensyve` from this marketplace (`integrations/claude-code`)
Codex CLI	integrations/codex-plugin
Cursor	integrations/cursor
OpenCode	integrations/opencode-plugin
Gemini CLI	`gemini extensions install https://github.com/major7apps/pensyve`
Copilot	`.copilot/` in repo root or `~/.copilot/` via `make install-copilot`

License

MIT — see LICENSE.

Star history

File tree

1160

wshobson/agentsView on GitHub ↗

.agents/
  plugins/
    marketplace.json
.claude-plugin/
  marketplace.json
.cursor/
.cursor-plugin/
  marketplace.json
  plugin.json
  plugins/
    accessibility-compliance.json
    agent-orchestration.json
    agent-teams.json
    api-scaffolding.json
    api-testing-observability.json
    application-performance.json
    arm-cortex-microcontrollers.json
    backend-api-security.json
    backend-development.json
    before-you-build.json
    block-no-verify.json
    blockchain-web3.json
    brand-landingpage.json
    business-analytics.json
    c4-architecture.json
    cicd-automation.json
    cloud-infrastructure.json
    code-documentation.json
    code-refactoring.json
    codebase-cleanup.json
    comprehensive-review.json
    conductor.json
    content-marketing.json
    context-management.json
    customer-sales-automation.json
    data-engineering.json
    data-validation-suite.json
    database-cloud-optimization.json
    database-design.json
    database-migrations.json
    debugging-toolkit.json
    dependency-management.json
    deployment-strategies.json
    deployment-validation.json
    developer-essentials.json
    dgx-spark-ops.json
    distributed-debugging.json
    documentation-generation.json
    documentation-standards.json
    dotnet-contribution.json
    error-debugging.json
    error-diagnostics.json
    file-conversion.json
    framework-migration.json
    frontend-mobile-development.json
    frontend-mobile-security.json
    full-stack-orchestration.json
    functional-programming.json
    game-development.json
    git-pr-workflows.json
    hermes-tweet.json
    hr-legal-compliance.json
    incident-response.json
    javascript-typescript.json
    julia-development.json
    jvm-languages.json
    kubernetes-operations.json
    llm-application-dev.json
    llm-finetuning.json
    machine-learning-ops.json
    meigen-ai-design.json
    multi-platform-apps.json
    observability-monitoring.json
    operating-kit.json
    payment-processing.json
    performance-testing-review.json
    plugin-eval.json
    pptx-deck-creation.json
    protect-mcp.json
    python-development.json
    quantitative-trading.json
    reverse-engineering.json
    review-agent-governance.json
    runapi-mcp.json
    security-compliance.json
    security-scanning.json
    seo-analysis-monitoring.json
    seo-content-creation.json
    seo-technical-optimization.json
    shell-scripting.json
    ship-mate.json
    signed-audit-trails.json
    skill-forge-essentials.json
    social-publishing.json
    startup-business-analyst.json
    systems-programming.json
    tdd-workflows.json
    team-collaboration.json
    ui-design.json
    unit-testing.json
    web-scripting.json
  rules/
    000-project-conventions.mdc
    010-python-tooling.mdc
    020-agent-skill-authoring.mdc
.gemini/
  settings.json
.github/
  CODE_OF_CONDUCT.md
  CONTRIBUTING.md
  dependabot.yml
  FUNDING.yml
  ISSUE_TEMPLATE/
    bug_report.yml
    config.yml
    feature_request.yml
    moderation_report.yml
    new_subagent.yml
  PULL_REQUEST_TEMPLATE.md
  workflows/
    claude-code-review.yml
    claude.yml
    code-quality.yml
    eval-report.yml
    validate.yml
.gitignore
.markdownlint.json
AGENTS.md
ARCHITECTURE.md
CLAUDE.md
CONTRIBUTING.md
docs/
  agent-skills.md
  agents.md
  architecture.md
  authoring.md
  harnesses.md
  plugin-eval.md
  plugins.md
  round-trip-results.md
  usage.md
gemini-extension.json
GEMINI.md
LICENSE
Makefile
plugins/
  accessibility-compliance/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      ui-visual-validator.md
    commands/
      accessibility-audit.md
    skills/
      screen-reader-testing/
        SKILL.md
      wcag-audit-patterns/
        references/
          details.md
        SKILL.md
  agent-orchestration/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      context-manager.md
    commands/
      improve-agent.md
      multi-agent-optimize.md
  agent-teams/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      team-debugger.md
      team-implementer.md
      team-lead.md
      team-reviewer.md
    commands/
      team-debug.md
      team-delegate.md
      team-feature.md
      team-review.md
      team-shutdown.md
      team-spawn.md
      team-status.md
    README.md
    skills/
      multi-reviewer-patterns/
        references/
          review-dimensions.md
        SKILL.md
      parallel-debugging/
        references/
          hypothesis-testing.md
        SKILL.md
      parallel-feature-development/
        references/
          file-ownership.md
          merge-strategies.md
        SKILL.md
      task-coordination-strategies/
        references/
          dependency-graphs.md
          task-decomposition.md
        SKILL.md
      team-communication-protocols/
        references/
          messaging-patterns.md
        SKILL.md
      team-composition-patterns/
        references/
          agent-type-selection.md
          preset-teams.md
        SKILL.md
  api-scaffolding/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      backend-architect.md
      django-pro.md
      fastapi-pro.md
      graphql-architect.md
    skills/
      fastapi-templates/
        references/
          details.md
        SKILL.md
  api-testing-observability/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      api-documenter.md
    commands/
      api-mock.md
  application-performance/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      frontend-developer.md
      observability-engineer.md
      performance-engineer.md
    commands/
      performance-optimization.md
  arm-cortex-microcontrollers/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      arm-cortex-expert.md
  backend-api-security/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      backend-architect.md
      backend-security-coder.md
  backend-development/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      backend-architect.md
      event-sourcing-architect.md
      graphql-architect.md
      performance-engineer.md
      security-auditor.md
      tdd-orchestrator.md
      temporal-python-pro.md
      test-automator.md
    commands/
      feature-development.md
    skills/
      api-design-principles/
        assets/
          api-design-checklist.md
          rest-api-template.py
        references/
          details.md
          graphql-schema-design.md
          rest-best-practices.md
        SKILL.md
      architecture-patterns/
        references/
          advanced-patterns.md
          details.md
        SKILL.md
      cqrs-implementation/
        references/
          details.md
        SKILL.md
      event-store-design/
        references/
          details.md
        SKILL.md
      microservices-patterns/
        references/
          details.md
        SKILL.md
      projection-patterns/
        references/
          details.md
        SKILL.md
      saga-orchestration/
        references/
          advanced-patterns.md
          details.md
        SKILL.md
      temporal-python-testing/
        resources/
          integration-testing.md
          local-setup.md
          replay-testing.md
          unit-testing.md
        SKILL.md
      workflow-orchestration-patterns/
        references/
          details.md
        SKILL.md
  before-you-build/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    README.md
    skills/
      before-you-build/
        references/
          risk-checklist.md
        SKILL.md
  block-no-verify/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    commands/
      block-no-verify.md
    skills/
      block-no-verify-hook/
        SKILL.md
  blockchain-web3/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      blockchain-developer.md
    skills/
      defi-protocol-templates/
        references/
          details.md
        SKILL.md
      nft-standards/
        references/
          details.md
        SKILL.md
      solidity-security/
        references/
          details.md
        SKILL.md
      web3-testing/
        references/
          details.md
        SKILL.md
  brand-landingpage/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    README.md
    skills/
      brand-landingpage/
        references/
          interview-framework.md
          state-and-pitfalls.md
          stitch-architecture.md
        SKILL.md
  business-analytics/
    .claude-plugin/
      plugin.json
    .codex-plugin/
      plugin.json
    agents/
      business-analyst.md
    skills/
      data-storytelling/
        references/
... 1592 more

wshobson-agents

Skills