cli-for-agents

An agent skill by cursor, from cursor/plugins. Tags: automation, cli, developer-tools, validation, workflow.

What it does

Designs or reviews CLIs so coding agents can run them reliably: non-interactive flags, layered --help with examples, stdin/pipelines, fast actionable errors, idempotency, dry-run, and predictable structure. Use when building a CLI, adding commands, writing --help, or when the user mentions agents, terminals, or automation-friendly CLIs.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add cursor/plugins --skill cli-for-agents

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/cli-for-agent/skills/cli-for-agents ~/.claude/skills/cli-for-agents

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only skill for designing agent-friendly CLIs. It contains no executable code, network behavior, filesystem access, or secret handling; the only notable theme is recommending standard CLI affordances like `--dry-run` and confirmation-bypass flags as part of the skill’s purpose.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	0 (none)	No scripts, shell commands, or code execution are present; the file is plain Markdown with examples like `mycli deploy --env staging`.
Network access	0 (none)	The skill does not download or send data to any remote host.
Filesystem reach	0 (none)	It does not read, write, or delete files; it only describes CLI design patterns.
Secrets & credentials	0 (none)	There is no handling of tokens, keys, passwords, `.env` files, or login sessions.
Privilege & persistence	0 (none)	No sudo, global installs, services, shell startup edits, or OS-level changes are requested.
Instruction hijack surface	0 (none)	The `--force` / `--yes` language is guidance for CLI UX, not an instruction for the agent to ignore its rules or follow remote content.
Irreversible actions	0 (none)	It describes how a CLI should expose options like `--dry-run` and confirmation bypasses, but it does not itself perform deploys, posts, payments, or other actions.
Transparency	0 (none)	The repository inventory shows a single readable Markdown file; there are no binaries, installers, or decoded-at-runtime blobs.

Before installing

Nothing to install or execute; review `SKILL.md` only.
If you adopt its patterns in a real CLI, decide up front whether `--force`/`--yes` and `--dry-run` are appropriate for your command set.

Rated 2026-10-19 by an automated review of 1 file from the skill's repository.

Source

Repository: cursor/plugins (all skills from this repository)
Path: cli-for-agent/skills/cli-for-agents/SKILL.md
Branch: main
Collection: cursor
Updated: 2026-09-23

create-verification-skill — Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
TUI Puppeteering with tmux — Use when automating or testing TUI/CLI applications - provides isolated tmux sessions with scripts for input, output capture, and state verification
control-cli — Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services.
principle-build-the-lever — Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks.
principle-encode-lessons-in-structure — Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
principle-make-operations-idempotent — Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries.