> ## Documentation Index > Fetch the complete documentation index at: https://developers.stellar.org/llms.txt > Use this file to discover all available pages before exploring further. # Stellar CLI for Agents > Use the Stellar CLI and CLI Skills to give your AI agents an agent-friendly wallet and native way to inspect, move, and manage assets on Stellar. Use the Stellar CLI and CLI Skills to give your AI agents an agent-friendly wallet and native way to inspect, move, and manage assets on Stellar. After following the [Quickstart](https://developers.stellar.org/docs/tools/cli/agent-cli/quickstart.md) to onboard your agent, you can use natural language to prompt your agent to use the Stellar CLI. Verified against `stellar-cli` 28.1.0. | What You Ask Your Agent | What Your Agent Executes | How It Works Under the Hood | | - | - | - | | **"Learn how to use the Stellar CLI"** | `stellar skill` | Dumps structured CLI conventions directly into the agent’s prompt/context window. | | **"How much USDC is in alice's account?"** | `stellar token balance` | Reads the balance in smallest units, or as a decimal with `--decimal`. No key setup needed. | | **"Send 20 USDC to `G...`"** | `stellar token transfer` | Executes an onchain transfer and returns the transaction hash. | | **"Limit agent spending to 50 USDC"** | `stellar token approve` | Grants a capped, time-bound allowance enforced directly onchain by the Stellar network. | | **"Draft a payment for my review"** | `stellar tx new payment --build-only` | Builds an unsubmitted transaction payload to a file for human sign-off or air-gapped execution. | ## Agent Ergonomics Browser wallets are hard for agents. The CLI provides four key agent primitive enhancements: * **Unified Asset Resolution:** Interacts with native XLM, SAC (Stellar Asset Contracts), or SEP-41 tokens using consistent identifiers (`CODE:ISSUER`, contract ID, or custom alias). * **Self-Scaffolding Context:** Running `stellar contract init` automatically generates an `AGENTS.md` guide in local project directories, giving LLMs instant awareness of local commands and tool rules. [Build and deploy a contract](https://developers.stellar.org/docs/tools/cli/agent-cli/guides/build-and-deploy-contracts.md#the-generated-agentsmd) covers what it contains and how to customize it. * **Structured JSON Outputs (`--output json`):** The `stellar token` commands return typed JSON, including transaction hashes and a typed error envelope. Coverage elsewhere varies, and `tx send` and `tx new` have no `--output` flag. [Output and errors](https://developers.stellar.org/docs/tools/cli/agent-cli/reference/output-and-errors.md) lists what each command supports. * **Onchain Diagnostic Errors:** When a transaction reverts, the CLI returns the contract's diagnostic event trail inside the error envelope. Agents can read *why* a transaction failed. ## Capability Surface Beyond only using the Stellar CLI as a wallet, your agent can also use the full power of CLI to interact with, build, and deploy contracts. Humans can read the full [Stellar CLI Manual](https://developers.stellar.org/docs/tools/cli/stellar-cli.md). | Functional Area | What Your Agent Can Do | CLI Commands | | - | - | - | | **System & Agent Context** | Check environment health and load usage rules into LLM context windows. | `stellar doctor` `stellar skill` | | **Balances & Metadata** | Read token holdings, inspect token names, symbols, and decimal precision. | `stellar token balance` `stellar token decimals / name / symbol` | | **Transfers & Payments** | Move tokens and get back the transaction hash, as a bare line by default or as JSON with `--output json`. | `stellar token transfer` | | **Spending Limits** | Set spending limits and audit active delegate approvals. | `stellar token approve` `stellar token allowance` | | **Transactions & Contracts** | Build raw operations, deploy Soroban contracts, and invoke custom smart contracts. | `stellar tx new ` `stellar contract deploy / invoke` | | **Safe Offline Operations** | Draft unsigned transactions for human-in-the-loop approval workflows. | `stellar tx new --build-only` | ## Safety Architecture Giving an agent financial execution power requires hard guardrails. The first two below are enforced by the network or by a human signer, not by the agent following instructions. The third is a convention your agent has to follow: 1. **Protocol Allowance Enforcement:** Primary funds remain in your treasury account. Issue your agent a capped allowance using `stellar token approve`. If the agent attempts to overspend, the Stellar ledger rejects the transaction. 2. **Human Approval Workflows:** Use `--build-only` flags on sensitive transactions. Your agent formats the payload into a file, leaving final signing authority to a human or air-gapped machine. 3. **Explicit Smallest-Unit Amounts:** `token transfer` and `token approve` take `--amount` in the token's smallest unit and do no conversion. Read `stellar token decimals` first and have the agent show its arithmetic before it sends. ## Where to go next * [Skills](https://developers.stellar.org/docs/tools/cli/agent-cli/skills.md) covers `stellar skill`, the built-in guide that teaches your agent the CLI's conventions. * [Delegate spending](https://developers.stellar.org/docs/tools/cli/agent-cli/guides/delegate-spending.md) is the page to read before any real money is involved. * [Build and deploy a contract](https://developers.stellar.org/docs/tools/cli/agent-cli/guides/build-and-deploy-contracts.md) takes your agent from `stellar contract init` to a deployed contract it can call. * [Authority & Security Model](https://developers.stellar.org/docs/tools/cli/agent-cli/reference/authority-model.md) is explicit about what the CLI does not protect you from. * [Architecture](https://developers.stellar.org/docs/tools/cli/agent-cli/reference/architecture.md) covers how the read and write paths differ, where state lives, and how to split building, signing, and submitting across machines. * [Output and errors](https://developers.stellar.org/docs/tools/cli/agent-cli/reference/output-and-errors.md) covers which commands emit structured JSON your agent can branch on, because the coverage is not uniform. * [Troubleshooting](https://developers.stellar.org/docs/tools/cli/agent-cli/reference/troubleshooting.md) for when something does not work.