Build with Coding Agents

Bundled skills that let Claude Code, Codex, and Cursor create, improve, evaluate, and maintain your agents.

Every template is designed for coding agents to drive the full agent-development lifecycle: create, improve, evaluate, maintain.

Everything on this page runs inside a cloned template. If you don’t have one running yet, pick a Starter 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
/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:

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: build an agent with /create-new-agent, then test it over MCP in the same session.

For a deployed platform, point the same command at your domain: uvx agno connect --url https://<your-domain>. Production is JWT-gated, so the command mints a service-account token (agno_pat_...) for the connection.

Evals

Lock in agent behavior with the eval suite in evals/. The evals run on the host machine, so set up the venv once:

./scripts/venv_setup.sh
source .venv/bin/activate

Then run:

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 <case>    # one case while iterating
python -m evals -v               # stream the full run with rich panels

Cases wrap AgentAsJudgeEval (LLM judge, binary pass/fail) and ReliabilityEval (tool-call assertions). Results log to Postgres, so run history shows up at 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_<thing> 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	Route to specialists, coordinate parallel work, synthesize results.
Workflows	Deterministic pipelines that run the same way every time.

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. Deterministic, 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.

See Scheduler for the cron API.