claude --permission-mode plan "Explain how FEATURE_NAME works and propose a test plan."
Replace FEATURE_NAME with a specific feature. The documented plan mode supports investigation before implementation.
Access & side effects
Starts a model session, reads permitted project context and consumes account usage. It may save session state. Plan mode is not a promise that no data leaves the machine.
codex --sandbox read-only --ask-for-approval on-request "Explain FEATURE_NAME with file references. Do not edit files."
Replace FEATURE_NAME with a narrow question. Read-only is a filesystem policy; on-request lets the agent request additional approval when needed.
Access & side effects
Starts a model session and can read project context, send it to the configured provider and save local session state. Approving an escalation can broaden what runs.
Enter this documented slash command inside an existing agy session. It opens the tool-permissions panel; it is not a command for your operating-system shell.
Access & side effects
Displays configuration in the current session. Changing settings in the panel can alter future tool access; simply opening it does not request a code change.
Run in a project with an existing uv.lock. Frozen uses the existing lockfile without updating it; offline disables network access. Missing required local information can make the command fail.
Access & side effects
Reads local project and lockfile metadata and prints the dependency tree. It does not run project code or intentionally update the lockfile.
After selecting and authenticating to the intended sandbox, this lists up to three customers. The CLI's documented default is sandbox requests; do not add --live for a development check.
Access & side effects
Makes an authenticated API read and prints customer data. It does not create a customer or charge a payment, but output may still contain sensitive information.
For the documented v1 CLI, list configured agents before choosing one. This illustrative command was not part of the runtime probes.
Access & side effects
Reads agent configuration and prints metadata; it does not ask a model to edit the project. Check the installed version because v2 uses a separate product line.
Assumes requests.json is an array with status, id and owner fields. --arg passes queued as data. This example uses a different fixture from the executed tests.
Access & side effects
Reads the named file and prints selected fields; it does not edit the file. The fields you choose can still contain confidential values.
duckdb -c "SELECT category, sum(amount) AS total FROM read_csv('expenses.csv') GROUP BY category ORDER BY category;"
Assumes expenses.csv has category and numeric amount columns. Check inferred types before using the totals. This illustrative file and query were not the executed fixture.
Access & side effects
Reads the local CSV and prints a result. Other SQL can write files or databases, and extensions can add network or executable behavior.
Run in a directory containing Terraform configuration. Prints formatting differences and reports whether changes are needed. This illustrative command was not part of the runtime probes.
Access & side effects
Reads local configuration and prints a diff; -check does not rewrite it or apply infrastructure changes.
Replace Notes with your vault name. Prints up to five files with the matching lines as path:line: text.
Access & side effects
Reads the vault through the running app and launches Obsidian if it is closed. Does not change notes.
No matching previews. Change or reset your filters.
How this interface works
A command-line interface, or CLI, is a way to operate software by typing commands in a terminal. It helps when a task needs to be precise, repeated or included in a script. Some CLIs also let an AI agent read and change a project.
Numbers show our editorial starting order within this collection. Each review explains its place. This is not an adoption leaderboard, performance benchmark or security score. Examples are illustrative. Separate evaluation records show local runtime checks, hosted connection checks and any unavailable coverage.
Review pull requests, inspect checks and manage repository work from the same terminal as your code.
Quick look
Why it’s here
An editorial first stop: the task is clear, read-only examples are useful immediately, and authentication and command effects are documented. This is not an adoption or overall-quality ranking.
Ask an agent to inspect a project, plan a change and work across files with explicit tool permissions.
Quick look
Why it’s here
An editorial starting point for supervised coding: natural-language tasks and documented permission modes make the workflow explainable. No model-performance comparison was run.
Inspect, change and test a local codebase with a coding agent whose filesystem access and approvals can be configured.
Quick look
Why it’s here
An editorial alternative for coding tasks with visible execution controls and a public CLI codebase. Position is not a measured comparison with other agents.
Work with Google's coding agents from the terminal, with project context, reviewable changes and configurable tools.
Quick look
Why it’s here
An editorial starting point for Google's current consumer coding-agent path. Documented migration and permission details support inclusion; no effectiveness or market-share ranking was measured.
Useful for
Google agent workflows
Reviewing project changes in a terminal
Before use
Antigravity CLI installed for the supported platform
Build and inspect containers so an application and its dependencies can be run in a defined environment.
Quick look
Why it’s here
An editorial infrastructure starting point: the output is tangible and inspection commands are clear, but daemon and image permissions add setup decisions.
Useful for
Local application dependencies
Repeatable development environments
Before use
Docker CLI and access to a compatible running daemon
Develop and manage Cloudflare Workers and related resources with project configuration that can be reviewed in code.
Quick look
Why it’s here
An editorial entry for teams using Cloudflare: clear project configuration and account inspection support repeatability, while platform-specific setup limits general usefulness.
Useful for
Workers development
Reviewable Cloudflare configuration
Before use
Installed Wrangler and its supported Node.js runtime
Check: Environment names do not guarantee isolation
Manage Python versions, project dependencies and isolated tools with a single command-line program.
Quick look
Why it’s here
An editorial starting point for Python work: requirements and dependency outputs are explicit. Its value is task-specific; no speed or compatibility benchmark was run.
Inspect Stripe API data and test webhook handling while keeping development activity separate from live payments.
Quick look
Why it’s here
An editorial specialist pick: it solves a concrete webhook-development problem with documented sandbox behavior. It is relevant primarily to Stripe integrations.
Inspect and manage AWS services through explicit commands, account profiles and structured output.
Quick look
Why it’s here
An editorial cloud-administration pick with clear identity and output controls. Broad capabilities require more account and permission setup than the earlier general tools.
Useful for
AWS inventory and troubleshooting
Repeatable service operations
Before use
AWS CLI version 2 installed for the platform
Check: The wrong profile can target the wrong account
Inspect Google Cloud projects and manage services with named configurations, explicit targets and structured output.
Quick look
Why it’s here
An editorial starting point for Google Cloud operations: explicit projects and structured output are useful, but service-specific setup and access controls require more preparation.
Useful for
Google Cloud inventory
Project and identity inspection
Before use
Installed Google Cloud CLI or an authorized Cloud Shell environment
Use a configurable terminal agent to explore code and prepare changes, with model choice and permission settings made explicit.
Quick look
Why it’s here
Adds a configurable terminal-agent option after the original ten entries, with model choice and explicit permission controls as its distinguishing workflow. The pinned v1 evaluation does not rank coding quality or cover v2. The original catalog order is preserved; this is an editorial position, not a measured adoption or security rank.
Useful for
Explaining an unfamiliar code path
Preparing a small change for human review
Before use
An installed OpenCode version matched to its documentation
Filter and reshape JSON in the terminal so API output becomes a small, readable answer or a predictable input for the next step.
Quick look
Why it’s here
Adds a broadly useful JSON transformation step that can turn other CLI outputs into a small, reviewable result. Placed before the more specialized additions for its simple local setup and clear input/output boundary. The original catalog order is preserved; this is an editorial position, not a measured adoption or security rank.
Search code and text from the terminal, with explicit control over ignored files, hidden files, regular expressions and output format.
Quick look
Why it’s here
Adds repository search alongside JSON processing: a practical way to locate evidence before an agent or developer edits code. Its inclusion rests on a distinct daily task, not a measured speed advantage. The original catalog order is preserved; this is an editorial position, not a measured adoption or security rank.
Run SQL over local files and database tables without setting up a database server, then inspect or export the result.
Quick look
Why it’s here
Adds local SQL analysis for data tasks that need joins or aggregation. It follows the smaller text-processing tools because SQL, file access and extension controls add more setup decisions. The original catalog order is preserved; this is an editorial position, not a measured adoption or security rank.
Describe infrastructure in configuration files, inspect a proposed plan and manage changes through providers and state.
Quick look
Why it’s here
Adds infrastructure planning and the review of state-dependent changes. It follows the local data tools because providers, backend access and sensitive artifacts require a more deliberate operating context. The original catalog order is preserved; this is an editorial position, not a measured adoption or security rank.
Inspect Kubernetes resources and prepare or apply manifests, with cluster context, namespace and permissions kept explicit.
Quick look
Why it’s here
Adds Kubernetes inspection and manifest preparation, a distinct workflow for readers who already operate clusters. Its placement reflects that specialized prerequisite and does not imply lower quality than general-purpose tools. The original catalog order is preserved; this is an editorial position, not a measured adoption or security rank.
Manage Neon Postgres projects, branches, roles and connections from a terminal, with JSON output for scripts and agents.
Quick look
Why it’s here
A capable first-party CLI with JSON output and branch-based workflows. Ranked after the Salesforce CLI because fewer small businesses run their own Postgres.
Search, read, create and append to notes in a local Obsidian vault from a terminal or script, through the running desktop app.
Quick look
Why it’s here
First-party CLI for Ion’s top-pick local notes app. Ranked after established developer CLIs because it needs a running desktop app and was not executed in this review.