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.
From claude-clinpx claudepluginhub richfrem/agent-plugins-skills --plugin claude-cliThis skill is limited to using the following tools:
acceptance-criteria.mdevals/evals.jsonevals/results.tsvfallback-tree.mdreferences/acceptance-criteria.mdreferences/fallback-tree.mdrequirements.txtscripts/run_agent.pySorts ECC skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using repo evidence like file extensions and configs. Creates trimmed install plan for project-specific needs.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
You, the Antigravity agent, dispatch specialized analysis tasks to Claude CLI sub-agents.
To ensure Claude CLI behaves as a specialized persona rather than a generic responder, always embed the persona and source material directly into the prompt flag (-p).
claude --model haiku-4.5 -p "$(cat agents/persona.md)
---SOURCE CODE---
$(cat target.py)
---INSTRUCTION---
Perform a full code review. Use severity levels: 🔴 CRITICAL, 🟡 MODERATE, 🟢 MINOR.
You are operating as an isolated sub-agent.
Do NOT use tools. Do NOT access filesystem." > review.md
run_agent.py (Cross-Platform)For reusable sub-agent execution, use the provided Python orchestrator which handles temp file assembly and prompt concatenation reliably across Windows, macOS, and Linux.
# Location: plugins/claude-cli/scripts/run_agent.py
python3 ./scripts/run_agent.py <PERSONA_FILE> <INPUT_FILE> <OUTPUT_FILE> "<INSTRUCTION>"
python3 ./scripts/run_agent.py agents/security-auditor.md target.py security.md \
"Find vulnerabilities. Use severity levels: 🔴 CRITICAL, 🟡 MODERATE, 🟢 MINOR."
agents/)These personas are mirrored from the Gemini and Copilot plugins to ensure consistent "Agentic" analysis across the ecosystem.
| Persona | Use For |
|---|---|
security-auditor.md | Red team, vulnerability scanning, threat modeling |
refactor-expert.md | Optimizing code for readability, performance, and DRY |
architect-review.md | Assessing system design, modularity, and complexity |
For rapid, cost-effective analytical sub-agent tasks, always specify --model haiku-4.5. It provides the best latency for "Inner Loop" code reviews.
If your prompt starts with YAML frontmatter (e.g., ---), some shell parsers might misinterpret the flag. Always prepend a newline to the prompt string when passing it to -p. (Note: The run_agent.py script handles this automatically).
Always add these instructions to your dispatch prompt to prevent the sub-agent from attempting to use external tools:
"You are operating as an isolated sub-agent. Do NOT use tools. Do NOT access filesystem. Only use the provided input."
python3 ./scripts/run_agent.py agents/refactor-expert.md target.py output.md "Refactor this code."