hiphapis

hiphapis/loopcraft

Plugin Claude Code

Loop engineering plugin for Claude Code — memory that survives sessions, self-correction loops, failure distillation.

hiphapis/loopcraft

Plugin Claude Code

Loop engineering for Claude Code — rubric+verifier self-correction, 5-stage memory protocol (fail→investigate→verify→distill→consult), autonomous backlog runner with pluggable sources (file/GitHub/Jira) and write-back.

hiphapis/loopcraft

Agent

Independent grader for loopcraft loop-tasks. Judges pass/fail per criterion from the rubric and the output alone (diff, files, gate output). Never receives the maker's reasoning or conversation. Read-only — makes no changes.

hiphapis/loopcraft

Hook

Runs when a session starts, executing session-start.sh via bash. From hiphapis/loopcraft.

hiphapis/loopcraft

Hook

Runs when the agent finishes a response, executing stop-gate.sh via bash. From hiphapis/loopcraft.

hiphapis/loopcraft

Hook

Runs before the context is compacted, executing pre-compact.sh via bash. From hiphapis/loopcraft.

hiphapis/loopcraft

Skill Claude CodeCodex

When there's a failure, bug, unexpected behavior, or important finding, distills it into a verified general rule saved under .loop/memory/. Invoke right after resolving a gate (test/typecheck) failure, right after fixing a verifier-graded fail, or right after pinning down a cause through debugging. Exclude failures…

hiphapis/loopcraft

Skill Claude CodeCodex

Onboards loopcraft into a project — scans the repo to detect gate commands, confirms the backlog and rubrics through an interview, then scaffolds the .loop/ structure. Run once per project, or when refreshing the config.

hiphapis/loopcraft

Skill Claude CodeCodex

Traverses the backlog unattended, applying the loop-task cycle (rubric · verifier · gate · Loop-Verified commit) to each item. Invoke only when the user explicitly starts an autonomous batch run — for individual work, use loop-task directly.

hiphapis/loopcraft

Skill Claude CodeCodex

Runs non-trivial implementation/fix work that needs a verifiable output through a rubric + independent verifier grading cycle. Invoke before starting code/docs work. Not for simple questions, exploration, or one-line fixes.