By truefoundry
Deploy, monitor, and manage ML infrastructure on TrueFoundry. Enforces reliable deployment workflows with automatic health verification, credential checks, and failure diagnosis.
Orchestrates TrueFoundry deployments with enforced workflow steps. Use when deploying services, applying manifests, or running multi-service deployments. Ensures workspace confirmation, secret creation, manifest validation, and post-deploy verification.
Diagnoses TrueFoundry deployment failures. Use when a deployment fails, pods are unhealthy, or services are unreachable. Fetches logs, identifies root causes, and suggests fixes.
Manages TrueFoundry roles, teams, and collaborators. Create custom roles, organize users into teams, and grant access to resources. Use when managing permissions, creating teams, or adding collaborators.
Manages TrueFoundry personal access tokens (PATs). List, create, and delete tokens for API auth and CI/CD.
Lists, inspects, and manages TrueFoundry application deployments. Shows status, health, and details for services, jobs, and Helm releases. Also handles requests to delete, remove, or destroy applications by directing users to the TrueFoundry UI.
Deploys applications to TrueFoundry. Handles single HTTP services, async/queue workers, multi-service projects, and declarative manifest apply. Supports `tfy apply`, `tfy deploy`, docker-compose translation, and CI/CD pipelines. Use when deploying apps, applying manifests, shipping services, or orchestrating multi-service deployments.
Fetches TrueFoundry documentation, API reference, and deployment guides. Use when the user needs platform docs or how-to guidance.
Executes bash commands
Hook triggers when Bash tool is used
Uses power tools
Uses Bash, Write, or Edit tools
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.
This plugin requires configuration values that are prompted when the plugin is enabled. Sensitive values are stored in your system keychain.
TFY_API_KEYTrueFoundry API key for authentication
${user_config.TFY_API_KEY}TFY_BASE_URLTrueFoundry platform URL (e.g., https://your-org.truefoundry.cloud)
${user_config.TFY_BASE_URL}Deploy, monitor, and manage ML infrastructure on TrueFoundry using AI coding assistants.
Works as a plugin for Claude Code and Codex CLI (with enforced workflows, automatic health verification, and failure diagnosis), and as rules + skills for Cursor.
Set your TrueFoundry credentials via environment variables or a .env file in your project root:
export TFY_BASE_URL=https://your-org.truefoundry.cloud
export TFY_API_KEY=tfy-...
No account yet? Run uv run tfy register to sign up. The tfy CLI and workspace selection are handled automatically -- skills install the CLI if missing and list your available workspaces at deploy time.
Add the marketplace and install the plugin:
/plugin marketplace add truefoundry/tfy-deploy-skills
/plugin install truefoundry@truefoundry-deploy-skills
Or interactively: /plugin → Discover tab → select truefoundry → Install now.
What you get:
Clone the repo and point Codex at it, or install via the Codex plugin system:
codex install truefoundry/tfy-deploy-skills
Enable hooks in your config.toml:
codex_hooks = true
Same hooks and skills as Claude Code. Agents are defined in AGENTS.md for Codex.
Copy the skills into Cursor's config directory:
npx skills add truefoundry/tfy-deploy-skills -g -a cursor -s '*' -y
What you get:
For any agent that supports the Agent Skills open format:
npx skills add truefoundry/tfy-deploy-skills -g -a claude-code -a cursor -a codex -s '*' -y
Or install for all detected agents:
npx skills add truefoundry/tfy-deploy-skills --all
Just ask your agent in plain English:
| Category | Skills |
|---|---|
| Deploy | applications, deploy, gitops, helm, jobs, llm-deploy, ml-repos, notebooks, service-test, ssh-server, tracing, volumes, workflows, workspaces |
| Operate | logs, monitor, status |
| Manage | access-control, access-tokens, docs, onboarding, secrets |
Installed skill names are namespaced as truefoundry-<skill> (e.g., truefoundry-deploy).
| Hook | Type | What It Does |
|---|---|---|
| Session Start | SessionStart | Verifies credentials, auto-installs/upgrades the tfy CLI, tests API connectivity, lists accessible workspaces |
| Block Deletes | PreToolUse | Blocks all DELETE API calls -- redirects users to the TrueFoundry dashboard for manual deletion |
| Auto-Approve API | PreToolUse | Auto-approves tfy-api.sh and tfy-version.sh calls so the agent does not prompt for each API request |
| Secret Scan | PreToolUse | Blocks commands containing hardcoded API keys, tokens, or credentials -- enforces tfy-secret:// references |
| Deploy Monitor | PostToolUse | Detects tfy apply/tfy deploy commands, polls deployment status with adaptive intervals, fetches logs on failure, verifies health on success |
| Verification Gate | Stop | Prevents the agent from finishing if a deployment is in progress or an endpoint is unreachable |
npx claudepluginhub truefoundry/tfy-deploy-skills --plugin truefoundryTrueFoundry AI Gateway plugin — onboarding, model routing, MCP servers, prompts, Skills Registry workflows, observability, guardrails, and codebase migration. Works across Claude Code, Codex, and Cursor.
Deploy ML models to production
Deploy ML models with FastAPI, Docker, Kubernetes. Use for serving predictions, containerization, monitoring, drift detection, or encountering latency issues, health check failures, version conflicts.
TrueFoundry AI Gateway plugin — onboarding, model routing, MCP servers, prompts, Skills Registry workflows, observability, guardrails, and codebase migration. Works across Claude Code, Codex, and Cursor.
Use this agent when setting up CI/CD pipelines, configuring Docker containers, deploying applications to cloud platforms, setting up Kubernetes clusters, implementing infrastructure as code, or automating deployment workflows. Examples: <example>Context: User is setting up a new project and needs deployment automation. user: "I've built a FastAPI application and need to deploy it to production with proper CI/CD" assistant: "I'll use the deployment-engineer agent to set up a complete deployment pipeline with Docker, GitHub Actions, and production-ready configurations."</example> <example>Context: User mentions containerization or deployment issues. user: "Our deployment process is manual and error-prone. We need to automate it." assistant: "Let me use the deployment-engineer agent to design an automated CI/CD pipeline that eliminates manual steps and ensures reliable deployments."</example>
Tower compute platform — run and deploy Python apps, pipelines, and AI agents
AI/ML development: LLM architecture, prompt engineering, ML ops, and NLP with production deployment focus