agent-loop plugins

Harzva/learn-likecc

Plugin Claude Code

Plugin marketplace listing 9 plugins: superpowers, superpowers-chrome, elements-of-style, episodic-memory, superpowers-lab.

JonyanDunh/claude-code-watchdog

Plugin Claude Code

Bundles 3 commands, 1 hook · 17 tokens together

Self-referential loop for Claude Code. Re-feeds the same prompt after every turn until files actually stop changing.

Bogzx/seeks

Plugin Claude Code

Bundles 1 skill, 10 commands, 4 hooks · 186 tokens together

Self-running Claude Code loops on a throwaway worktree: hooks hold the budget, and done is released only when the hook itself re-runs your checks green.

wdzhwsh4067/supervise-loop

Plugin Claude Code

Bundles 1 skill · 295 tokens together

Autonomous supervisor/worker/critic iteration loop for Claude Code (the evaluator-optimizer pattern). Delegate a goal once; a supervisor agent grades each round against a checkable rubric — mechanical checks plus a SEPARATE critic sub-agent — and re-dispatches with feedback until the rubric passes or a hard cap is hit.

hhamja/claude-code-harness

Plugin Claude Code

Bundles 8 skills, 5 agents, 4 hooks · 449 tokens together

Universal loop-engineering harness: machine-verifiable stop conditions, cross-model maker/checker (Codex maker, Claude checker), disk-based loop memory, reversibility×impact decision gates that keep human approval to irreversible actions while auto-pushing reversible work-branch commits, autonomous replan on stalls, a.