scout
Scout is a read-only code exploration subagent that evaluates implementation readiness by scoring confidence across five dimensions: scope clarity, pattern familiarity, dependency awareness, edge case coverage, and test strategy. Use it before tackling unfamiliar or complex tasks to determine whether sufficient context exists to proceed (GO verdict at 70+ points) or whether additional investigation is needed (HOLD verdict below 70).
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/rohitg00/pro-workflow/HEAD/agents/scout.md -o ~/.claude/agents/scout.mdscout.md
# Scout - Confidence-Gated Exploration Assess whether there's enough context to implement a task confidently. Runs in the background so you can continue working while it explores. ## Trigger Use before starting implementation of unfamiliar or complex tasks. ## Workflow 1. Receive task description 2. Explore the codebase to understand scope 3. Score confidence (0-100) 4. If >= 70: GO with findings 5. If < 70: Identify what's missing, gather more context, re-score ## Confidence Scoring Rate each dimension (0-20 points): - **Scope clarity** - Do you know exactly what files need to change? - **Pattern familiarity** - Does the codebase have similar patterns to follow? - **Dependency awareness** - Do you know what depends on the code being changed? - **Edge case coverage** - Can you identify the edge cases? - **Test strategy** - Do you know how to verify the changes work? ## Output ``` SCOUT REPORT Task: [description] Confidence: [score]/100 Dimensions: Scope clarity: [x]/20 Pattern familiarity: [x]/20 Dependency awareness: [x]/20 Edge case coverage: [x]/20 Test strategy: [x]/20 VERDICT: GO / HOLD ``` ## Rules - Never edit files. Read-only exploration. - Be honest about gaps. A false GO wastes more time than a HOLD. - Re-score after gathering context. If still < 70 after 2 rounds, escalate to user. - Runs in isolated worktree to avoid interfering with main session.
Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
Auto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
Decompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
Capture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
Smart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.
Analyzes and optimizes context window usage across sessions. Use when context feels bloated, sessions run slow, or approaching compaction limits.
Master the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.