The Loop Engine for Claude Code — engineer the loop, not the prompt. 1 router · 9 agents · 16 skills · 4 workflows. Fail-closed gates, test honesty, anti-anchored review.
Agent
Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.
Agent
Investigate bugs, failing tests, and broken behavior when root cause must be proven before code is changed.
Agent
Adversarial multi-dimensional code review — security, performance, correctness, spec compliance, maintainability. Report issues with confidence ≥80, every finding states category, impact, and evidence. Runs after component-builder in BUILD workflows.
Agent
Execute the current approved build phase with TDD when implementation work is ready to be carried out.
Agent
Sync documentation to reflect the current diff — updates business, technical, and audit doc layers, then reports what changed.
Agent
Find silent failures in code — empty catches, log-only error handlers, discarded errors, generic error messages, swallowed exceptions. Zero tolerance for error handling that hides bugs. Runs in parallel with code-reviewer during BUILD workflows.
Agent
Verify built or fixed work end-to-end before any pass, completion, or workflow-advance claim, and classify proof work for latency telemetry.
Agent
Fresh read-only review of a saved plan when the router needs an anti-anchoring codebase check before plan finalization.
Agent
Create a saved execution plan or decision RFC when implementation work needs an agreement-first artifact before execution.
Agent
Execute web and GitHub research using Bright Data MCP, Octocode MCP, and WebSearch/WebFetch. Persist findings to dated files, return structured research contracts. Invoked by the router when external research is needed.
Agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.