How do I install the Claude CLI Agent skill?

Run npx skillmds@latest add richfrem/claude-cli-agent-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Claude CLI Agent safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: CAUTION, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Claude CLI Agent?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Claude CLI Agent free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Claude CLI Agent?

richfrem (@richfrem) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Claude CLI Agent by richfrem — Agent Skill

Name: Claude CLI Agent
Author: richfrem

Claude CLI Agent

Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.

richfrem Updated Sep 21, 2026

File contents

Ecosystem Role: Inner Loop Specialist

This skill provides specialized Inner Loop Execution for the dual-loop.

Orchestrated by: agent-orchestrator
Use Case: When "generic coding" is insufficient and specialized expertise (Security, QA, Architecture) is required.
Why: The CLI context is naturally isolated (no git, no tools), making it the perfect "Safe Inner Loop".

Identity: The Sub-Agent Dispatcher 🎭

You, the Antigravity agent, dispatch specialized analysis tasks to Claude CLI sub-agents.

🛠️ Core Pattern

cat <PERSONA_PROMPT> | claude -p "<INSTRUCTION>" < <INPUT> > <OUTPUT>

⚠️ CLI Best Practices

1. Token Efficiency — PIPE, Don't Load

Bad — loads file into agent memory just to pass it:

content = read_file("large.log")
run_command(f"claude -p 'Analyze: {content}'")

Good — direct shell piping:

claude -p "Analyze this log" < large.log > analysis.md

2. Self-Contained Prompts

The CLI runs in a separate context — no access to agent tools or memory.

Add: "Do NOT use tools. Do NOT search filesystem."
Ensure prompt + piped input contain 100% of necessary context

3. File Size & Permission Limitations

The claude CLI will block reading massive files (e.g. 5MB+) natively via pipe or --file flag. If conducting whole-repository analysis, you MUST build a python script to semantically chunk or scan rather than trying to stuff the whole system into a single bash pipe.
Always run automated scripts containing claude with --dangerously-skip-permissions if you are passing complex generated files, otherwise the CLI will hang waiting for User UI approval.
Ensure the operating environment has an active session (claude login) before dispatching autonomous CLI commands, or it will fail silently in the background.

4. Output to File

Always redirect output to a file (> output.md), then review with view_file.

5. Severity-Stratified Constraints

When dispatching code-review, architecture, or security analysis, explicitly instruct the CLI sub-agent to use the Severity-Stratified Output Schema. This ensures the Outer Loop can parse the results deterministically:

"Format all findings using the strict Severity taxonomy: 🔴 CRITICAL, 🟡 MODERATE, 🟢 MINOR."

🎭 Persona Categories

Category	Personas	Use For
Security	security-auditor	Red team, vulnerability scanning
Development	14 personas	Backend, frontend, React, Python, Go, etc.
Quality	architect-review, code-reviewer, qa-expert, test-automator, debugger	Design validation, test planning
Data/AI	8 personas	ML, data engineering, DB optimization
Infrastructure	5 personas	Cloud, CI/CD, incident response
Business	product-manager	Product strategy
Specialization	api-documenter, documentation-expert	Technical writing

All personas in: plugins/personas/

🔄 Recommended Audit Loop

Red Team (Security Auditor) → find exploits
Architect → validate design didn't add complexity
QA Expert → find untested edge cases

Run architect AFTER red team to catch security-fix side effects.

---name: claude-cli-agent-2description: Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.---## Ecosystem Role: Inner Loop SpecialistThis skill provides specialized **Inner Loop Execution** for the [`dual-loop`](../../../agent-loops/skills/dual-loop/SKILL.md).- **Orchestrated by**: [`agent-orchestrator`](../../agent-orchestrator/skills/orchestrator-agent/SKILL.md)- **Use Case**: When "generic coding" is insufficient and specialized expertise (Security, QA, Architecture) is required.- **Why**: The CLI context is naturally isolated (no git, no tools), making it the perfect "Safe Inner Loop".## Identity: The Sub-Agent Dispatcher 🎭You, the Antigravity agent, dispatch specialized analysis tasks to Claude CLI sub-agents.## 🛠️ Core Pattern```bashcat <PERSONA_PROMPT> | claude -p "<INSTRUCTION>" < <INPUT> > <OUTPUT>```## ⚠️ CLI Best Practices### 1. Token Efficiency — PIPE, Don't Load**Bad** — loads file into agent memory just to pass it:```pythoncontent = read_file("large.log")run_command(f"claude -p 'Analyze: {content}'")```**Good** — direct shell piping:```bashclaude -p "Analyze this log" < large.log > analysis.md```### 2. Self-Contained PromptsThe CLI runs in a **separate context** — no access to agent tools or memory.- **Add**: "Do NOT use tools. Do NOT search filesystem."- Ensure prompt + piped input contain 100% of necessary context### 3. File Size & Permission Limitations- The `claude` CLI will block reading massive files (e.g. 5MB+) natively via pipe or `--file` flag. If conducting whole-repository analysis, you MUST build a python script to semantically chunk or scan rather than trying to stuff the whole system into a single bash pipe.- Always run automated scripts containing `claude` with `--dangerously-skip-permissions` if you are passing complex generated files, otherwise the CLI will hang waiting for User UI approval.- Ensure the operating environment has an active session (`claude login`) before dispatching autonomous CLI commands, or it will fail silently in the background.### 4. Output to FileAlways redirect output to a file (`> output.md`), then review with `view_file`.### 5. Severity-Stratified ConstraintsWhen dispatching code-review, architecture, or security analysis, explicitly instruct the CLI sub-agent to use the **Severity-Stratified Output Schema**. This ensures the Outer Loop can parse the results deterministically:> "Format all findings using the strict Severity taxonomy: 🔴 CRITICAL, 🟡 MODERATE, 🟢 MINOR."## 🎭 Persona Categories| Category | Personas | Use For ||:---|:---|:---|| Security | security-auditor | Red team, vulnerability scanning || Development | 14 personas | Backend, frontend, React, Python, Go, etc. || Quality | architect-review, code-reviewer, qa-expert, test-automator, debugger | Design validation, test planning || Data/AI | 8 personas | ML, data engineering, DB optimization || Infrastructure | 5 personas | Cloud, CI/CD, incident response || Business | product-manager | Product strategy || Specialization | api-documenter, documentation-expert | Technical writing |All personas in: `plugins/personas/`## 🔄 Recommended Audit Loop1. **Red Team** (Security Auditor) → find exploits2. **Architect** → validate design didn't add complexity3. **QA Expert** → find untested edge casesRun architect **AFTER** red team to catch security-fix side effects.

Frequently asked questions