> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cordango.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Building with an agent

> Cordango is designed to be driven by an AI coding agent.

An App Definition is a document with a published schema and an offline checker. That makes it an
unusually good target for an AI agent: it can write, check its own work, and be told precisely what
it got wrong, all without a database, a model API or a deploy.

This section has a tuned starting prompt for each of the common agents. They differ, because the
tools differ. Read this page first, because the reasoning behind all of them is the same.

## Your workspace already briefs the agent

```bash theme={null}
cordango new support
```

That writes `CLAUDE.md` and `AGENTS.md` into the workspace root, with the same generated text in
both. Two conventions want two filenames, and a workspace that taught two agents different rules
would produce source only one of them could maintain.

<Note>
  This is the single most important thing on the page. The instructions are already there. Your
  prompt does not need to re-explain Cordango, and it should not try.
</Note>

What those files teach is the **workflow**, not the vocabulary: how to find out, rather than a copy
of the schema. That is deliberate, and it is what stops an agent's context filling up with 212 KB of
JSON Schema.

## The rules they install

Every prompt in this section leans on these, so they are worth reading once.

**Discover, do not guess.** `cordango inspect` for what exists, `cordango vocabulary` for what may
be written. Both answer from the installed build, so they cannot drift from what the CLI will
accept.

**Never read the schema, never read the binary.** If `cordango vocabulary` cannot answer a
question, that is a gap worth reporting rather than working around.

**Check constantly.** `cordango check` calls no model and touches no database. It is free. Run it
after every change.

**One aggregate per change.** It keeps diffs reviewable, and it is what `--scope` enforces.

**Stable keys.** Renaming an entity or field key is not supported, because nothing rewrites the
references to it. Add and remove deliberately instead.

**The agent does not accept its own work.** `cordango apply` writes to the working tree. A person
reads `git diff` and stages it.

## Every command speaks JSON

```bash theme={null}
cordango help --json
cordango inspect --app support --json
cordango check --json
```

`--json` works on all of them. `cordango help --json` in particular is how an agent discovers the
command surface without a human pasting a README into its context.

## The shape of a good prompt

Short, and about the job. The workspace supplies the rest.

```text theme={null}
Add a "priority" field to the ticket entity: a select with low, normal, high and urgent,
defaulting to normal. Then show it as a column on the tickets table.

Run cordango check when you are done. Do not commit.
```

Note what is absent. No explanation of what Cordango is, no YAML example, no schema excerpt, no list
of field types. All of that is one `cordango vocabulary field` away, and an agent that looks it up
gets the version that matches the installed CLI.

## Pick your agent

<CardGroup cols={2}>
  <Card title="Claude Code" icon="terminal" href="/ai/claude">
    Reads `CLAUDE.md` automatically. The path of least resistance.
  </Card>

  <Card title="Codex" icon="code" href="/ai/codex">
    Reads `AGENTS.md`. Same workspace, same instructions.
  </Card>

  <Card title="Cursor" icon="arrow-pointer" href="/ai/cursor">
    Needs a rules file pointing at the workspace instructions.
  </Card>

  <Card title="GLM" icon="robot" href="/ai/glm">
    Strongest with explicit, sequenced instructions.
  </Card>
</CardGroup>