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

# Coding Agents

> Run Deepline from Codex, Claude Code, Cursor, Gemini CLI, Antigravity, Hermes, OpenClaw, and other coding agents that can use a shell.

[Human guide: work with your agent →](https://deepline.com/docs/human/sdk-v2/coding-agents.md)

> [!NOTE]
>
> Install Deepline in the agent runtime and produce one reviewed pilot in the
> intended workspace.

Use this when you want an agent to run GTM work without opening the Deepline UI.

## Pick the integration path

| Agent environment | Best path | Notes |
| - | - | - |
| Claude Code | Deepline skill + CLI | Best covered today. See [Claude Code](https://deepline.com/docs/sdk-v2/claude-code.md). |
| Codex | Deepline skill + CLI | Install the hosted skills, then run commands from the agent terminal. |
| Cursor | Deepline skill + CLI | Install hosted skills, or point Cursor at the skill markdown files. |
| Grok Bot | Deepline skill + CLI | Install from the agent chat. See [Grok Bot](https://deepline.com/docs/grok-bot.md). |
| Gemini CLI | Deepline skill + CLI | Supported by the hosted skill installer. |
| Antigravity | Deepline skill + CLI | Supported by the hosted skill installer. |
| Hermes Agent / Hermes IDE | CLI | Use the Deepline CLI from the shell. Deepline does not publish a hosted Hermes skill target yet. |
| OpenClaw | CLI or MCP | Run the Deepline CLI from its shell tools or register Deepline through its MCP client registry. |
| Any other shell-capable agent | CLI | Install, authenticate, then give the agent the exact command to run. |

The rule is simple: if the agent can run shell commands, it can run Deepline.
Use skills where the agent supports them. Use the plain CLI everywhere else.

## Ask the agent to install Deepline

Give the agent this instruction:

```text theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
Install and set up the official Deepline CLI globally from npm (package: deepline) by following https://code.deepline.com/INSTALL.md.
```

The guide makes the agent check its environment, install `deepline@latest`,
run `deepline setup`, handle the persistent project-local fallback in a
restricted sandbox, complete browser authorization, and verify CLI, skills,
auth, and workspace state.

For a direct terminal install: check `npm --version` and use the matching command.

For npm 11.16 or newer:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
npm install -g --allow-scripts=esbuild deepline@latest && npm exec --yes --allow-scripts=esbuild --package=deepline@latest -- deepline setup --json
```

For older npm:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
npm install -g deepline@latest && npm exec --yes --package=deepline@latest -- deepline setup --json
```

In a sandbox with no writable global npm prefix, install into the project
instead:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
npm install --prefix .deepline/runtime --global --no-audit --no-fund --include=optional deepline@latest && ./.deepline/runtime/bin/deepline setup --scope local --json
```

`deepline setup` installs the hosted skill bundle for the detected agent and
keeps it current. The hosted installer supports Codex, Claude Code, Cursor,
Gemini CLI, and Antigravity. For an unknown agent it installs the bundle for all
supported targets. Hermes remains CLI-only.
OpenClaw uses the CLI or MCP and does not have a hosted Deepline skill target.

## Give the agent a concrete job

Create `leads-pilot.csv` with [CSV-safe record selection](https://deepline.com/docs/sdk-v2/batch-csv.md#2-select-representative-csv-records) before the pilot commands.

Good agent instructions name the file, output file, run name, row range, and
tool payload.

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline search --type prebuilts "verified work email CSV waterfall"
deepline describe prebuilt/name-and-domain-to-email-waterfall-batch --json
# Create leads-pilot.csv using CSV-safe record selection before this run.
deepline plays run prebuilt/name-and-domain-to-email-waterfall-batch --csv leads-pilot.csv
```

If the pilot looks right, run the same checked Play on the full file:

```bash theme={"languages":{"custom":["/languages/deepline-prompt.json"]}}
deepline plays run prebuilt/name-and-domain-to-email-waterfall-batch --csv leads.csv
```

Do not ask the agent to guess flags or Play names. Have it inspect the Play,
prepare the pilot, and run the exact sequence above.

## Review the pilot before expanding it

Ask the agent to report the following before processing the full input:

* The exact Play or tool contract and the identifiers used to match records.
* Accepted, unresolved, and failed rows, with evidence for the acceptance rule.
* Recorded Deepline usage and the selected managed or BYOK mode.
* Proposed external changes and the fields the workflow is permitted to write.
* The retry and review policy for uncertain destination outcomes.

Include representative missing, ambiguous, and conflicting inputs in the
pilot. A successful authoring check does not prove the business result.

Keep external writes disabled in the authored logic until their policy is
ready. This is a workflow control you implement, not a universal Play dry-run
flag. Save the run ID so later inspection observes the same work.

## Use the GTM agent repo

For repo-backed agent workflows, start from the Deepline GTM agent project:

> **[deepline-gtm-agent](https://github.com/getaero-io/deepline-gtm-agent)**
>
> Reference repo for improving Deepline GTM agent workflows across coding
> agents.

Use that repo when you want versioned prompts, reusable workflows, or a shared
agent setup that works across Codex, Claude Code, and other shell-capable
coding agents.

## Troubleshooting

> **The agent says deepline is not found**
>
> Ask the agent to follow `https://code.deepline.com/INSTALL.md` in that
> environment. It will use a persistent project-local install when sandbox
> policy blocks a global installation.

> **Setup or authentication failed**
>
> Read the failed phase and exact retry command from `deepline setup --json`. If
> setup reports a diagnostic command, run it. Otherwise, in a project-local
> installation, use `./.deepline/runtime/bin/deepline doctor --scope local   --json`. after a global install, use `deepline doctor --json`.

> **The agent invented a Deepline command**
>
> Stop and check the internal content canonicals before running it. For
> enrichment, use the command shape on this page.

## Verify this task

Confirm CLI availability and effective authorization. Review pilot source IDs, accepted outcomes, exceptions, and scoped usage before scaling.

Ask your agent to explain a failed check before repeating work or expanding the scope.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.