By tony
Run prompts through individual AI CLIs — codex/GPT, gemini, and cursor/agent with fallback support
Delegate a task to OpenAI's GPT via the Codex CLI. Use this skill when the user explicitly asks to use Codex, GPT, or OpenAI for a task, or when you determine that GPT would provide better results for a specific task (e.g., tasks requiring OpenAI-specific strengths). Detects the codex binary, falls back to agent --model gpt-5.4-high if unavailable.
Delegate a task to Cursor's agent CLI. Use this skill when the user explicitly asks to use Cursor or the agent CLI for a task, or when you determine that Cursor's agent would provide better results for a specific task. Requires the agent binary — there is no fallback for this skill.
Delegate a task to Google's Gemini via the gemini CLI. Use this skill when the user explicitly asks to use Gemini or Google's model for a task, or when you determine that Gemini would provide better results for a specific task (e.g., tasks requiring Gemini-specific strengths). Detects the gemini binary, falls back to agent --model gemini-3.1-pro if unavailable.
Use when running a prompt through OpenAI GPT directly. An alternative invocation point for /model-cli:codex — both use the same backend (codex binary or agent --model gpt-5.4-high fallback). Use this or /model-cli:codex interchangeably.
A third-party Claude Code plugin marketplace providing language-agnostic AI / agentic workflow plugins for DX efficiency.
Warning: Review plugins before installing. Anthropic does not control plugin contents and cannot verify they work as intended.
Repository: tony/ai-workflow-plugins
| Plugin | Category | Description |
|---|---|---|
| commit | Development | Create git commits following project conventions with format enforcement and safety checks |
| loom | Development | Weave prompts across Claude, Gemini, and GPT in parallel — plan, execute, review, and synthesize |
| rebase | Development | Automated rebase onto trunk with conflict prediction, resolution, and quality gate verification |
| changelog | Productivity | Generate categorized changelog entries from branch commits and PR context |
| tdd | Testing | TDD bug-fix workflow — reproduce bugs as failing tests, find root cause, fix, and verify |
| model-cli | Development | Run prompts through individual AI CLIs — codex/GPT, gemini, and cursor/agent with fallback support |
| pr | Development | Generate and review gold-standard pull request descriptions with structured headings, tables, and test plans |
| research | Learning | Clone and study your project's dependencies at the exact versions you use — source repos with version-pinned git worktrees |
| tailwind | Design | Detect and fix inconsistent spacing in Tailwind CSS layouts — container fragmentation, margin/gap mixing, padding asymmetry, and more |
Add the marketplace:
/plugin marketplace add tony/ai-workflow-plugins
You can also browse available plugins with /plugin > Discover.
Then install any plugin:
/plugin install commit@ai-workflow-plugins
/plugin install loom@ai-workflow-plugins
/plugin install rebase@ai-workflow-plugins
/plugin install changelog@ai-workflow-plugins
/plugin install tdd@ai-workflow-plugins
/plugin install model-cli@ai-workflow-plugins
/plugin install pr@ai-workflow-plugins
/plugin install research@ai-workflow-plugins
/plugin install tailwind@ai-workflow-plugins
Every plugin in this repository is language-agnostic. Commands do not hardcode
language-specific tools like pytest, jest, cargo test, or ruff. Instead, they
reference the project's own conventions by reading AGENTS.md or CLAUDE.md at
runtime to discover:
This means the same plugin works whether your project uses Python, TypeScript, Rust, Go, or any other language.
Scripts use uv to manage Python dependencies.
Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
or:
wget -qO- https://astral.sh/uv/install.sh | sh
See uv installation docs for other methods.
uv run ./scripts/marketplace.py lint
Dry-run:
uv run ./scripts/marketplace.py sync
Write changes to marketplace.json:
uv run ./scripts/marketplace.py sync --write
uv run ./scripts/marketplace.py check-outdated
Lint:
uv run ruff check ./scripts/
Format check:
uv run ruff format --check ./scripts/
Type check:
uv run basedpyright ./scripts/
See the official Claude Code plugin docs for authoring guides, component schemas, and marketplace publishing.
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub tony/ai-workflow-plugins --plugin model-cliGenerate categorized changelog entries from branch commits and PR context
Generate and review gold-standard PR descriptions and merge commit messages with structured headings, tables, and test plans
Detect and fix inconsistent spacing in Tailwind CSS layouts — container fragmentation, margin/gap mixing, padding asymmetry, and more
Automated rebase onto trunk with conflict prediction, resolution, and quality gate verification
Clone and study your project's dependencies at the exact versions you use — source repos with version-pinned git worktrees
AI-to-AI collaboration — review code, brainstorm ideas, and debate plans across Gemini, Codex, and Ollama
Hub plugin for cc-multi-cli-plugin: contains the companion runtime, subagents, setup wizard, and customization skills.
Multi-LLM integration for second opinions and task delegation
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
Fuse the Claude Code model with OpenAI Codex and Google Gemini: query all three in parallel, then Claude judges, synthesizes, and acts.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.