ClaudeHut

Generates two or more genuinely distinct solution options for a problem and recommends one. General-purpose ideation — any problem type (feature, bug, refactor, performance, design). Consumes the Discover phase's context + reuse decision; returns the candidate enforcement set for code tasks. Do NOT write code.

Persistence-layer correctness — JPA mappings, fetch strategies, migration safety (Flyway/Liquibase), transaction boundaries. Use in the Review phase, spawned by claudehut:review, on changes to entities, repositories, or migrations.

Read-only codebase query agent for the Discover phase. Use when you need to understand an unfamiliar area, locate where something is implemented, or map the modules a task will touch so candidate solutions adapt to this codebase. Do NOT use to write code or propose fixes — it only reports.

Executes the plan test-first under the project's conventions. Use in the Implement phase for multi-file changes that benefit from an isolated worktree. Honors every rule that auto-loads for the files it touches.

Extracts candidate learnings for the Learn phase and keeps the reuse index and committed memory index current. The deterministic merge/dedup/promote/prune is done by a script after you return. Carries project-scoped auto-memory.

Use to generate and weigh solution approaches for a problem, after discovery has grounded the context. Produces two or more genuinely distinct options scored on trade-offs, recommends one, and (for code tasks) assembles the enforcement set the rest of the workflow audits against. General-purpose ideation — works for any problem type; not tied to a specific stack.

Use in the Learn phase at the end of every task, before declaring done - dispatches the learner agent to record what was learned (conventions, pitfalls, reuse points, decisions) to the cross-session store and refresh the committed memory index, then closes the phase. Runs inline on the main thread (it owns the state write).

Use once per project before starting work (or when ClaudeHut reports no codebase index) to bootstrap ClaudeHut for a Java/Spring repository - detects the stack, generates the project memory + index + path-scoped rules, and wires the always-load @import slice. Invoked as /claudehut:init. Idempotent.

Use at the start of every session and whenever beginning a coding task in a Java/Spring backend - establishes the ClaudeHut 7-phase agentic workflow, the complexity-tier routing that lets small tasks skip deliberation phases, and the laws that govern which skills and rules must fire. Injected at session start; also re-anchor mid-session with /claudehut:workflow.

Use as the FIRST phase of EVERY coding task, before brainstorming - grounds the work in the existing codebase (entry points, key types, structure) and proves whether something reusable already exists. Produces the reuse-scan artifact the write gate requires and the reuse DECISION (adopt / extend / new). Runs inline on the main thread; trivial tier uses the inline 3-grep variant. Skip ONLY for pure documentation/comment edits with zero production-code change.

8 hooks across 7 events