Agent
Executes the plan test-first under the project's conventions, in an isolated worktree. Honors every rule that auto-loads for the files it touches.
2 9d ago A 37 tokens
Agent
Extracts candidate learnings for the Learn phase and keeps the reuse + memory indexes current. Carries project-scoped auto-memory.
2 9d ago A 33 tokens
Agent
Observability review — metrics, tracing, and SLO instrumentation on new/changed endpoints, listeners, jobs, and outbound clients. Read-only.
2 9d ago A 38 tokens
Agent
JVM and data-access performance review — N+1 queries, missing indexes, blocking calls on reactive paths, allocation hot spots. Read-only.
2 9d ago A 37 tokens
Agent
Reviews a drafted plan against its spec BEFORE the user-approval gate — coverage, no placeholders, implementability, reuse honored. Returns a verdict.
2 9d ago A 36 tokens
Agent
Turns the implementation spec into a file-level, executable, test-first plan. Writes the plan file; never production code.
2 9d ago A 30 tokens
Agent
Finds existing implementations to adopt or extend before any new code is written, and produces the reuse-scan artifact the write gate requires.
2 9d ago A 35 tokens
Agent
General code review — correctness, readability, conventions, dead code, over-engineering — against the enforcement set and project rules.
2 9d ago A 31 tokens
Agent
Spring-security-aware review — OWASP, authn/authz, injection, secret handling. Spawned by claudehut:review on controller/auth/security/data-exposure changes.
2 9d ago A 43 tokens
Agent
Runs the test suite and diagnoses failures with real output — the fresh evidence a completion claim requires.
2 9d ago A 26 tokens
Command
Show the ClaudeHut learning scoreboard — measured memory health (store size, reinforcement, effectiveness/recurrence, quality) so you can tell whether the agent is actually getting smarter across sessions. One-shot, read-only.
2 9d ago A 44 tokens
Agent
Benchmark-only BACKGROUND worktree agent (background: true). Records start/end epochs around a fixed-duration work block, commits, returns DONE with branch+sha.
2 9d ago A 0 tokens
Agent
Benchmark-only foreground worktree agent. Records start/end epochs around a fixed-duration work block, commits, returns DONE with branch+sha.
2 9d ago A 34 tokens
SessionStart
86Hook
Runs when a session starts on startup, resume, clear, compact and fork, executing bootstrap.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
Hook
Runs when you submit a prompt, before the agent sees it, executing inject-phase.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
Hook
Runs to expand your prompt before the agent sees it for (claudehut:)?(implement, discover and brainstorm) tool calls, executing record-skill-expansion.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
PreToolUse
89Hook
Runs before the agent uses a tool for Write, Edit, MultiEdit, Agent and Skill tool calls, executing gate-write.sh, record-agent-dispatch.sh and record-skill.sh (3 commands). From taipt1504/claudehut.
2 9d ago A
tokens not measured
PostToolUse
90Hook
Runs after a tool call finishes for Write and Edit tool calls, executing format-java.sh and lint-reuse.sh (4 commands). From taipt1504/claudehut.
2 9d ago A
tokens not measured
Hook
Runs when a tool call fails for Bash tool calls, executing record-failure.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
Stop
92Hook
Runs when the agent finishes a response, executing gate-done.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
Hook
Runs when a subagent starts, executing record-dispatch.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
Hook
Runs after instructions files are loaded, executing record-rules-loaded.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
SubagentStop
95Hook
Runs when a subagent finishes, executing verify-subagent.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured
PreCompact
96Hook
Runs before the context is compacted, executing persist-state.sh. From taipt1504/claudehut.
2 9d ago A
tokens not measured