deep-loop
🔌PluginSungmin-Cho/claude-deep-suite
|Loop Engineering control plane over the deep-suite — discovers work, routes to sibling deep-* plugins as maker/checker episodes, keeps durable lock-safe loop state, and hands off to fresh sessions autonomously with proof-gated terminal states and proposal-only external actions.
Part of
Sungmin-Cho/claude-deep-suite
Installation
/plugin marketplace add Sungmin-Cho/claude-deep-suite/plugin install deep-loop@claude-deep-suiteMore from this repository9
LLM-native knowledge wiki — ingest sources (files, URLs, notes, Obsidian vaults) into linked Markdown pages with source provenance, then query the accumulated knowledge; self-linting and self-healing, for Claude Code and Codex.
Cross-project semantic memory — harvests sibling-plugin artifacts into reusable memory cards (rule-based plus LLM distillation) and surfaces task-specific briefs, with opt-in cross-runtime hook capture and multi-pass redaction.
Evidence-Driven Development Protocol — a single-command Brainstorm → Research → Plan → Implement → Test → Integrate workflow with TDD enforcement, receipt-based evidence, and a hard separation between planning and coding, for Claude Code and Codex.
Harness layer for Claude Code & Codex: plan-first development, independent review, durable long-running orchestration, and knowledge capture — nine composable plugins.
Goal condition compiler — evaluates a long-running task, reshapes it to fit, scouts prerequisites, and compiles a ready-to-paste native /goal condition for Claude Code and Codex, with multi-plugin synergy recipes.
Document gardening + authoring — scan/garden/audit + generate·restructure CLAUDE/AGENTS/ARCHITECTURE docs, for Claude Code and Codex.
Autonomous Experimentation Protocol — a measured outer loop that proposes, runs, and selects code changes against a fitness metric, with lineage and session history, for Claude Code and Codex.
Independent Evaluator — reviews your changes in a separate agent context (Claude/ultracode multi-agent fan-out + optional Codex review/adversarial + agy) and returns an APPROVE / CONCERN / REQUEST_CHANGES verdict plus an evidence-based response protocol. v1.12.2: thin-dispatcher Phase B — review-mode body extracted to on-demand references; the command is now a route-first thin router (1136→53 lines) and respond/init no longer load the workflow skill (behavior-preserving).
Cross-plugin harness diagnostics + suite telemetry — aggregates receipts, health reports, and harnessability metrics emitted by sibling deep-suite plugins into one dashboard, with optional OTLP export.