> ## Documentation Index > Fetch the complete documentation index at: https://agno-v2-codex-docs-audit-20260719-0149.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Build with Coding Agents > Bundled skills that let Claude Code, Codex, and Cursor set up, create, improve, evaluate, and maintain your agents. Every template is designed for coding agents to drive the full agent-development lifecycle: set up, create, improve, evaluate, maintain. Everything on this page runs inside a cloned template. If you don't have one running yet, [pick a Starter](/deploy/introduction) first. The skills live in `.agents/skills/`. Claude Code picks them up on clone through a committed `.claude/skills` symlink; other harnesses like Codex and Cursor can symlink the same folder. Invoke a skill by name (`/create-new-agent`) or describe the task and the coding agent matches it. ## Skills | Skill | What it does | Who drives | | --------------------- | ---------------------------------------------------------------------------------------- | --------------- | | `/setup-platform` | Configures the environment, starts AgentOS, builds the first agent, and connects the UI. | You + the agent | | `/create-new-agent` | Scaffolds an agent, registers it in `app/main.py`, smoke-tests it live. | You + the agent | | `/extend-agent` | Adds a tool or capability, refines instructions, fixes a known bug. | You | | `/improve-agent` | Derives probes from the agent's `INSTRUCTIONS`, judges responses, edits until they pass. | The agent | | `/eval-and-improve` | Runs the eval suite, diagnoses failures, fixes in scope until green. | The agent | | `/review-and-improve` | Sweeps for drift between docs, code, and config. Auto-fixes mechanical drift. | The agent | ## Your platform as an MCP tool Coding agents edit the platform's code and call its live agents over MCP. Register your AgentOS with the MCP clients on your machine: ```bash theme={null} uvx agno connect ``` It auto-detects Claude Code, Claude Desktop, Codex, and Cursor and registers `http://localhost:8000/mcp`. To check the connection, open one of those apps and ask: "can you access my agentos mcp?". Your coding agent can then call `run_agent`, `run_team`, and `run_workflow` against the live platform. For a deployed platform, point the same command at your domain: `uvx agno connect --url https://`. `agno connect` writes client credentials according to the endpoint's authentication. It writes tokenless entries for an unauthenticated MCP endpoint. It mints scoped service-account tokens (`agno_pat_...`) for a token-protected endpoint when the AgentOS has a REST admin credential that can authorize the mint. For an OAuth-enabled endpoint, it writes tokenless entries and prints one-time browser sign-in steps for supported clients. Use `--pat` when a headless client needs a service-account token on an OAuth-enabled AgentOS; minting still requires a REST admin credential or an existing admin PAT. With the built-in OAuth provider, `MCP_CONNECT_SECRET` is the secret entered on the AgentOS consent page. Coding clients use OAuth tokens from that flow or a separately minted PAT. ## Evals Lock in agent behavior with the eval suite in `evals/`. The evals run on the host machine, so set up the venv once: ```bash theme={null} ./scripts/venv_setup.sh source .venv/bin/activate ``` Then run: ```bash theme={null} python -m evals --tag smoke # fast checks of the self-driving surfaces python -m evals --tag release # broader pre-release confidence python -m evals --name # one case while iterating python -m evals -v # stream the full run with rich panels ``` Cases wrap [AgentAsJudgeEval](/evals/agent-as-judge/overview) (LLM judge, binary pass/fail) and [ReliabilityEval](/evals/reliability/overview) (tool-call assertions). Results log to Postgres, so run history shows up at [os.agno.com](https://os.agno.com) next to sessions and traces. If a case fails, run `/eval-and-improve`. ## Agent patterns The bundled agents demonstrate three patterns to copy: | Pattern | Example | When to use | | ---------------- | ---------------------------- | ----------------------------------------------------------------------------------------------- | | Direct tools | `agents/web_search.py` | The agent needs fine-grained control over each tool call. | | Context provider | `agents/platform_manager.py` | You want many tools collapsed into one `query_` interface that hands off to a sub-agent. | | Studio builder | `agents/agent_builder.py` | Users create and refine components from chat; deletes keep a confirmation gate. | ## Teams and workflows | Pattern | When to use | | -------------------------------- | ------------------------------------------------------------------- | | [Teams](/teams/overview) | Route to specialists, coordinate parallel work, synthesize results. | | [Workflows](/workflows/overview) | Processes with defined, repeatable control flow. | Agents for open questions, teams for routing, workflows for processes. ## Scheduled tasks The scheduler is on by default. Two reference workflows are registered out of the box: | Workflow | What it does | Default | | ---------------- | ------------------------------------------------------------------------------------------------- | ----------------------------------------------- | | Deployment check | Daily readiness report: database, auth, scheduler, MCP, Slack config. Fixed checks, no LLM calls. | On. Disable with `ENABLE_DEPLOY_CHECK=False`. | | Run evals | Daily smoke-tag eval run. Uses model calls. | Off. Enable with `ENABLE_SCHEDULED_EVALS=True`. | Scheduler claims expire after 300 seconds without renewal. The bundled eval workflow permits runs up to 900 seconds, so a long eval can overlap with a reclaimed run even on one replica. Keep the target idempotent or use an external scheduler. See [Scheduler](/agent-os/scheduler/overview) for the cron API.