loop-auditor
01cbdreamer11/CB-loop-kit-claude-plugin
Agent
Adversarial reviewer. Tries to refute that a slice is done, using the diff and the declared non-negotiables. Read-only.
A session-based working method for coding agents: plan in thin complete slices, build one at a time, verify by observing real behaviour, hand off cleanly. Skills + agents + 2 hooks for Claude Code.
cbdreamer11/CB-loop-kit-claude-plugin
Agent
Adversarial reviewer. Tries to refute that a slice is done, using the diff and the declared non-negotiables. Read-only.
cbdreamer11/CB-loop-kit-claude-plugin
Agent
Implements one slice completely inside an assigned file tree. Reads real code before writing. Never publishes.
cbdreamer11/CB-loop-kit-claude-plugin
Agent
Decides open technical questions against real documentation and real APIs on the web, never from memory. Read-only.
cbdreamer11/CB-loop-kit-claude-plugin
Agent
Splits an epic into thin vertical slices that are each safe to leave forever. Writes the plan to disk. Does not write product code.
cbdreamer11/CB-loop-kit-claude-plugin
Agent
Cheap, fast reader. Maps what exists in the codebase and reports back facts, not opinions. Read-only.
cbdreamer11/CB-loop-kit-claude-plugin
Agent
Runs the project's verification contract against real behaviour and judges honestly - verified, gap, or failed. Does not implement fixes.