AI Agent CLI Guide for a First Local Coding Task

See how a terminal AI coding agent reads, edits and tests a local project. Practice on a disposable folder with scoped permissions and a small reviewable diff.

What a CLI coding agent can do

Abstract outlined cubes on a warm geometric background

Read project context

The agent can inspect files available to it to find the implementation and existing tests.

Flowing line illustration suggesting movement and rhythm

Propose or make changes

A tool may offer planning and editing modes. Read the permission settings before granting write access.

Black starburst illustration on a pale peach background

Run and report checks

A local test run gives you concrete output to compare with the expected behavior and file diff.

Practice on a local toy project

Colorful printed posters arranged as a creative mood board

Greeting behavior

Change one blank-input case in a tiny Python project that has a unit test suite.

Illustrated scene of two people sitting together

README correction

Update one usage example and compare it with the existing local script.

Scrapbook collage of friends photographed together

Test-only exercise

Add an edge-case test for a reversible local task and review the failure message before editing the code.

Run one scoped edit

Creator planning a project on a laptop

Prepare the scratch folder

Create or copy a tiny repo containing greeting.py and its tests. Leave credentials and production files outside it.

Person wearing headphones while working at a laptop

Review permissions

Check the CLI’s docs for read, write, command and network scope. Begin with a plan before allowing the intended edit.

Person holding a tablet displaying illustrated music artwork

Check the evidence

Read git diff, run python3 -m unittest and compare the valid-name and blank-name outcomes. Record a clean screen demo only if useful.

Frequently Asked Questions

What complete prompt or practical brief can I copy?

Work only in this disposable local Git repository. Read greeting.py and the existing tests. First propose a plan for using “Hello, friend!” when the name is blank or whitespace. Then update only greeting.py and its test file, keeping the existing behavior for a valid name. Run python3 -m unittest locally. Use no network, credentials, installs or external services. Show the changed files, test result and Git diff for review before any commit.

What is an AI agent CLI?

It is a terminal interface that can invoke tools such as project file reads, scoped edits and local commands, depending on the product and configured permissions.

Is a prompt the same as a permission rule?

A prompt describes the task. The CLI’s actual settings control tool access. As one example, see Claude Code’s official permission documentation for allow, ask and deny rules.

Do I need dependencies or network access for this test?

The example tests can use Python’s built-in unittest module with the files already in the disposable repo. Use locally installed tools and keep the test offline.

What should I verify before committing?

Review that only the named files changed, the new test covers blank and whitespace input, and the existing valid-name behavior still passes. Then decide whether to commit.

Turn the local review into a short walkthrough

Use CapCut to trim a clean recording of the test result and diff after reviewing every frame for private information.