Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Claude Cli

ASecurity

Shell out to claude CLI.

4 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsgoshellbashcode-review

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/25/2026

$npx -y skills add colinmollenhour/dotfiles --skill claude-cli --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Claude Cli?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Claude Cli
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/colinmollenhour-claude-cli/badge)](https://www.skillsdirectory.com/skills/colinmollenhour-claude-cli)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: claude-cli
user-invocable: false
description: 'Shell out to claude CLI.'
allowed-tools: Bash(claude *)
---

# Claude CLI

Use the `claude` CLI to send prompts to Claude models from shell-based workflows — typically when the current host is OpenCode, or when a sub-agent must run outside the native `Agent` tool.

## Basic Invocation

```bash
claude --model opus --print --output-format text -- "Your prompt here"
```

Key flags:
- `--model` — model family: `opus`, `sonnet`, or `haiku`.
- `--print` — non-interactive; prints response and exits.
- `--output-format text` — plain text response; also accepts `json`, `stream-json`.
- `--` — separates flags from the prompt (required when the prompt starts with `-`).

## Adding Context via File

```bash
claude --model opus --print --output-format text \
  --append-system-prompt .tmp/context.md \
  -- "Short user-facing prompt here"
```

- `--append-system-prompt <file>` — appends file content to the system prompt. Use for large shared context (diffs, specs, MR content) without bloating the prompt argument.
- Real instructions go in the file; the trailing `-- "..."` stays brief and human-readable.

## Effort and Session Options

```bash
claude --model opus --print --output-format text \
  --effort max \
  --name "MBOT: code-review opus" \
  -- "Perform the review as instructed."
```

- `--effort max` — increases thinking budget for complex reasoning tasks.
- `--name "..."` — names the session in the Claude UI; useful for auditing batch runs.

## Agent Selection

```bash
claude --agent general --model opus --print --output-format text -- "Prompt"
```

- `--agent general` — uses the general-purpose agent profile with tool access. Omit for a plain completion with no tools.

## Capture Output

```bash
claude --model opus --print --output-format text -- "Prompt" > .tmp/claude-output.txt 2>&1
```

Redirect to a file for consumption by aggregation steps. Capturing both stdout and stderr (`2>&1`) avoids lost error messages.

## Model Reference

| Flag value | Model |
|---|---|
| `opus` | Claude Opus 5.5 — strongest reasoning |
| `sonnet` | Claude Sonnet 4.6 — balanced speed and quality |
| `haiku` | Claude Haiku 4.5 — fastest, cheapest |

## Host-Specific Routing

- **OpenCode host**: `claude` CLI is the **only** path for Claude-family models. Do not use `colin-mbot-opus` or similar subagents — those are for non-Claude models only.
- **Claude Code host**: prefer the native `Agent` tool; use this CLI as a fallback when the Agent tool is unavailable.
- **Codex host**: shell out to `claude` for any Claude-family model.

## Caveats

- `--print` mode does not support interactive tool approval; the agent runs with permissions granted at session level.
- Long prompts should be written to a file and passed via `--append-system-prompt`, not inlined in the argument.

Attribution

colinmollenhourcolinmollenhour
View sourceSee grades on GitHubMore from colinmollenhour →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →