Shell Tool · engineering · Sentinel

Build an Agent

Spin up an autonomous agent on the agent-runtime satellite — try templates first, custom build only if no fit.

Updated today

View as MarkdownsentinelsonnetstandardMax 12 turns

Overview

Two-phase agent builder. Phase 1: agent templates lists 25 curated patterns (support, research, digest, review, status-page-monitor, etc.); if any match the user's goal, use it. Phase 2 (fallback): follows build-agent/SKILL.md to scaffold from scratch with the right tool palette (compose-tools/SKILL.md keeps the integration list minimum-viable to avoid model confusion). Returns the agent id and an inspect URL.

When to use this

user wants an autonomous agent that runs on a schedule
user says 'build me a support bot' / 'I want an agent that monitors X' / 'set up an automation that runs every morning'
user has a recurring workflow to automate

When NOT to use this

user wants a one-off task (no scheduling, no autonomy) → use whatever tool fits
user wants to inspect an EXISTING agent → run `agent show <id>` directly

Example prompts

build me a customer-support agent that watches new tickets

set up an agent that gives me a daily digest of competitor moves

I want an agent that monitors my status page and alerts on outages

create an agent that reviews PRs

Inputs and output

Inputs

Field	Description
`goal`	what the agent should do, in one sentence
`schedule`	optional cron or natural-language frequency

Output

Agent id, the chosen template (or 'custom'), and the agent-runtime inspect URL.

Runtime profile

What the engine commits when this skill runs.

Property	Value	Meaning
Model tier	`sonnet`	The balanced default model class. Trades quality against cost for the vast majority of skill runs.
Cost class	`standard`	The balanced default model. Right for most skills.
Turn budget	`12`	Hard cap on tool-calling iterations before the engine forces a final answer.
Execution	`synchronous`	Runs inside the live turn; result lands in the same response.

Under the hood

Tools the engine exposes to this skill and integrations it needs.

Resource	Kind
`shell_exec`	tool

Tags: engineering, agent, automation

Execution template

Shell tools dispatch via a command template. The model substitutes user inputs into the placeholders before firing the underlying tool.

shell_execbash

1agent templates; if match: agent create from template; else follow build-agent/SKILL.md per compose-tools rules

Related skills

Skill	What it does
Spin up a Web App	Scaffold a fresh web app in /work, start the dev server, surface the live preview URL.
Clone a Website	Fire ultron-capture: spider the site, deploy a branded clone, surface the URL when ready.
Deploy to Cloudflare	Ship the current /work to Pages, Workers, or Containers — then verify the live URL.
Push to GitHub	Initialize /work as a git repo, create the GitHub repo, push, return the URL.
Swap Page Sections	Reorder <section> blocks in a minified HTML file with byte-level safety.
Refactor Across Files	Multi-file string operations with quote and escape safety — uses bun -e, not sed.

Invoking this from an agent

Three paths reach this skill. From the chat UI, a user can type the persona slash command followed by a natural request and the discovery step resolves to this skill automatically. From the MCP server, fetch the skill detail with get_skill({id: "build-agent"}) and then invoke it through the agent runtime once the authenticated tier ships. From your own code, hit /docs/skills/build-agent/llm.txt for the token-efficient markdown body and feed it to your model directly.

Note

Every skill page has a canonical permalink and a markdown alternate that LLM crawlers consume via Accept: text/markdown. The full machine-readable catalog lives at /.well-known/agent-skills/index.json.