Example Deep Rescue — Research agent for Claude Code
Optional, explicitly authorized final investigation of a named blocker after advanced analysis.
How to install Example Deep Rescue
Installs to ~/.claude/agents/ceponatia-rolesync-example-deep-rescue.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ceponatia/rolesync/HEAD/.claude/agents/example-deep-rescue.md -o ~/.claude/agents/ceponatia-rolesync-example-deep-rescue.md Restart Claude Code, or start a new session, for it to be picked up.
What Example Deep Rescue does
name: "example-deep-rescue" description: "Optional, explicitly authorized final investigation of a named blocker after advanced analysis. Disabled by default; not an automatic routine coding or architecture route." model: "fable" tools: ["Read", "Grep", "Glob", "Bash", "Edit", "Write", "Skill"] permissionMode: "default" maxTurns: 32 skills: ["example-escalate"] effort: "max" isolation: "worktree"
Read root an
Alternatives in Research
- Deep Dive — Use this agent when you need comprehensive analysis, investigation, or exploration of code, architecture, or t 1.8k ★
- Fable Worker Sonnet — Fable stage worker for tasks needing real reasoning — research synthesis, nontrivial code, analysis, document 837 ★
- Troubleshoot Agent — Deep research agent for build failures and JUCE problems 209 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Researcher Sonnet
Default research tier. Standard codebase investigation — how a feature is wired, what a change would touch, wh
Portfolio Manager
Final trading decision maker with paper trading execution. Use after gathering analysis from other agents to m
Compass Review
Final reviewer after Arbiter's verdict, checking plan adherence, research alignment, requirements coverage, ac
M Code Context Scout
Performs wide codebase investigation in a separate context and returns a compact map. Use before large refacto
Deepseek Researcher
Read-only DeepSeek agent for architecture analysis, repository exploration, dependency investigation and imple
Comparative Analyzer
Comparative analysis agent — performs side-by-side codebase comparison, architecture A/B analysis, competitive
Related Skills
Envoy Rescue
Delegate investigation, an explicit fix request, or follow-up rescue work to the Codex rescue subagent
Pi Plugin Cc
Drive the Pi coding agent from Claude Code or Codex: multi-model review panels, model racing, incremental & sh
Agentlas Call
Prepare explicitly named Agentlas Hub or Cloud agents.