AI / Agent entry point
Complete Deno development tasks safely with minimal context
Reading order
- Read
/en/llms.txtfor the page index. - Load one task page as Markdown, such as
/en/docs/core/permissions.md. - Use
/en/llms-full.txtonly for cross-cutting work. - Before editing, inspect
deno.json(c),deno.lock,package.json, imports, tasks, and CI. - After editing, run
fmt --check,lint,check, and relevant tests, then report exact commands.
Task routing
| Goal | Read first | Then |
|---|---|---|
| Run/debug TypeScript | Runtime | Permissions |
| Install a dependency | Dependencies | CLI and config |
| Change a monorepo | Workspaces | Production baseline |
| Add tests | Testing | Built-in tools |
| Migrate Node | Node migration | Common errors |
| Build an AI service | AI apps | Permissions |
| Call OpenAI | Deno + OpenAI | AI apps |
| Build MCP tools | MCP server | Agent architecture |
| Design an agent loop | Agent architecture | Agent rules |
| Run untrusted agent code | Deno Sandbox | Permissions |
| Release a service | Deployment decisions | target platform's official docs |
Invariants
- Do not replace the repository's package or task conventions before reading them.
- Do not grant -A to silence a permission error; identify the exact resource.
- Running TypeScript does not replace `deno check` in CI.
- Keep deno.lock unless the user explicitly approves dependency resolution changes.
- Verify current Deno, framework, and platform behavior from primary sources.
- Never print environment values or pass untrusted text through a shell command.
Deno also publishes deno.com/agents.md and denoland/skills. This site's rules focus on task routing and do not replace those official skills.