A dev pipeline for Claude Code that will not call work done until tests, lint and a security audit all exit zero. Seven specialists run it, for 1.1k tokens of always-on context.
★not rated 15 1mo agoA
tokens not measured
originalMIT
Pre- and post-implementation validation with parallel subagents: /replan validates plans before execution, /recheck verifies implementations match the plan. On real code changes /recheck also runs a full /code-review high pass. Includes a per-run audit trail, lessons-learned feedback loop (interactive + autonomous)…
AI development loop — orchestrator distributes tasks to headless workers, independent auditor verifies, structural enforcement auto-blocks downstream on upstream failure. Full-cycle validated with 10-scenario test harness.
DAG-based lossless context management for Claude Code. Every message from every session is persisted in a SQLite vault with FTS5 search. Summaries form a directed acyclic graph - nothing is ever lost.
★not rated 15 4mo agoA
tokens not measured
originalMIT
A Claude Code plugin that keeps project memory across coding sessions. It records project information, decisions, and past tasks so later work can use that context.
★not rated 15 1mo agoA
tokens not measured
originalMIT
Gene set enrichment analysis via the Enrichr API: MCP tools for enrichment and library discovery, plus an enrichr-api skill for raw API work the tools do not cover (reverse gene lookup, library download, batch enrichment).
AI-powered editorial style guide generation from blog content and article compliance review system. Analyze published blog articles to extract consistent patterns, then review content with 8 specialized agents in parallel.
★not rated 15 7d agoA
tokens not measured
originalMIT
Skills for AI-assisted project orchestration following best practices for software development lifecycle, architecture documentation, and quality automation.
★not rated 15 10d agoA
tokens not measured
originalMIT
Batch-process GitHub issues end-to-end: contrarian-gated planning, per-task implementation with quality loops, test loops, PR review, and squash-merge into a human-reviewed batch PR. Discovers and uses the target project's own agents.
★not rated 15 1mo agoA
tokens not measured
originalMIT
Unified spec-to-execution workflow system. Combines spec rigor, autonomous execution, and native task orchestration with parallel agent dispatch. Swarms-ready architecture.
★not rated 15 yesterdayA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: