> For the complete documentation index, see [llms.txt](https://docs.talus.network/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.talus.network/talus-docs-v2.1.0/guides/tap-development/build-agent-package-and-workflow.md).

# Build an Agent Package and Workflow

{% hint style="info" %}
**Audience:** Nexus adopters and integrators.

**Goal:** Assemble a Talus Agent Package (TAP) Agent package and DAG artifact using authenticated network objects, then verify the public bindings before scheduling work.
{% endhint %}

### Prerequisites

* Complete [Developer Setup](/talus-docs-v2.1.0/guides/getting-started/setup.md) and retain the operator-supplied authenticated objects file.
* A TAP package scaffold, registered Tool FQNs, and a DAG design that matches the target deployment schemas.
* Agent custody or the public authority required for the intended binding operation.

#### Configure the authenticated network objects

Do not hand-write a flat deployment TOML or duplicate registry/ToolCashier IDs. Reuse the authenticated artifact from setup:

```bash
OBJECTS_FILE="${OBJECTS_FILE:?Set OBJECTS_FILE to the operator-supplied objects file}"
OBJECTS_SHA256=<operator-supplied-64-hex-sha256>
test -f "$OBJECTS_FILE"
test "${#OBJECTS_SHA256}" = 64
printf '%s  %s\n' "$OBJECTS_SHA256" "$OBJECTS_FILE" | sha256sum -c -
nexus conf set --nexus.objects "$OBJECTS_FILE"
```

The SDK consumes a structured operator-supplied `NexusObjects` value. In the pinned SDK it contains `chain_id`, `network_id`, shared roots for ToolRegistry, NetworkAuth, AgentRegistry, LeaderRegistry, priority-fee vault, and RuntimeAuthority; object identities for the corresponding admin/authority capabilities; and `us_token`. Treat all IDs as deployment-specific; this guide does not publish substitute values. If the operator-supplied digest check fails, stop before `nexus conf set` and do not continue with TAP publication or mutation.

#### Build the package and DAG artifact

1. Start from [Scaffold a Talus Agent Package](/talus-docs-v2.1.0/guides/tap-development/scaffold-and-package.md).
2. Define the package state and Agent-owned skill intent.
3. Author a DAG whose Tool FQNs, schemas, and verifier modes are inspected in the target deployment.
4. Validate the skill artifact before publication, then publish and bind it through [Publish, Register, Bind](/talus-docs-v2.1.0/guides/tap-development/publish-register-bind.md).

The expected artifacts are the TAP package publication, DAG/skill artifact, registered Tool bindings, and Agent skill binding. This guide intentionally stops before scheduling: Task, Occurrence, Execution, ExecutionPayment, and verifier readback belong to the dedicated execution guides.

#### Verification and recovery

Inspect the registered Tool FQNs and Agent skill binding after publication. If an objects-file checksum, Tool schema, or binding does not match the target deployment, stop and correct that artifact before scheduling; do not construct replacement global registry or ToolCashier configuration by hand.

#### Next

Continue with [Execute and Verify Transfer](/talus-docs-v2.1.0/guides/tap-development/execute-and-verify-transfer.md) or [Schedule an Asset-Management Flow](/talus-docs-v2.1.0/guides/agent-usage/schedule-asset-management-flow.md) for the Task → Occurrence → Execution lifecycle.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.talus.network/talus-docs-v2.1.0/guides/tap-development/build-agent-package-and-workflow.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.