Depth Limit Tester — Development agent for Claude Code
Reports what tools are available at the current subagent depth.
How to install Depth Limit Tester
Installs to ~/.claude/agents/davila7-claude_subagents-depth-limit-tester.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/davila7/claude_subagents/HEAD/.claude/agents/depth-limit-tester.md -o ~/.claude/agents/davila7-claude_subagents-depth-limit-tester.md Restart Claude Code, or start a new session, for it to be picked up.
What Depth Limit Tester does
name: depth-limit-tester description: Reports what tools are available at the current subagent depth. Used to verify the 5-level nesting limit in Claude Code. tools: Read, Agent model: claude-haiku-4-5-20251001
You are a depth limit tester.
When invoked:
- List every tool that is available to you in this context
- Report whether the Agent tool is present or absent
- Attempt to use the Agent tool to spawn a subagent with the prompt "ping"
- Report the result — success, error, or sil
Alternatives in Development
- Accessibility Runtime Tester.Agent 31k ★
- Auth Tester — Authentication and session management testing agent 812 ★
- Lxc Provisioning Tester — Функциональное тестирование LXC контейнера MikoPBX после загрузки 571 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Omg Orchestrator
Coordinates ULW/RALPH workstreams for oh-my-grok. Decomposes goals, spawns depth=1 Grok-native workers, integr
Cdp Ninja Tiger Knockdown
Aggressive stress tester - breaking point discovery, chaos engineering, structural assault, boundary testing.
Usage Reporter
Reads real Claude Code usage from ~/.claude/stats-cache.json. Reports daily/weekly token usage by model, cache
Decider
Assigns an integrity level and a loop depth to a classified unit, and disposes escalations the engine routes t
Exploit Developer
Stage 8 of Vulpine. Given the issue reports from stage 7, think through reliable exploit chains that combine t
Gui Tester
Run GUI tests and report results. Use after GUI changes to verify nothing is broken.
Related Skills
Verbosity
How much prose an answer carries - brief, default or verbose. Reports the current level when called with no ar
Code Review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). M
Agent Seatbelt
Defense-in-depth for AI coding agents: macOS sandbox via Apple Seatbelt, plus content-level PII hooks for Clau