Context-shielding, cost-tiered delegation for Claude Code: high-volume work runs in specialized subagents on the cheapest tier a grader can check, returning summaries that keep the main context small. Ships a tiered agent roster, an orchestration skill, three workflows (survey, audit, and a manifest-driven build), and.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Generates structured requirements documents from a project idea or feature description, including functional requirements, non-functional requirements, Gherkin acceptance criteria, edge cases, and out-of-scope items.
★not rated 1 yesterdayA
tokens not measured
originalMIT
Auto-records Claude Code sessions as structured Obsidian notes + Daily Note entries (via the SessionEnd/PreCompact hooks and /done), and ships the obsidian-vault agent — the unified handler for all Obsidian vault work (create, edit, search, organize notes, tasks, canvases, bases). Configure with…
★not rated 1 3mo agoA
tokens not measured
originalMIT
Gentle notification sounds: a rising two-note chime when Claude needs your confirmation, a resolved major arpeggio when a task completes. Sounds are user-replaceable.
★not rated 1 1mo agoA
tokens not measured
originalMIT
Voice + OS notifications when Claude is waiting on you or finished a turn. Cross-platform, focus-aware, with quiet hours and 10s debounce to keep noise low.
★not rated 1 2mo agoA
tokens not measured
originalMIT
An always-on operating protocol for coding agents: build only what's asked, surface ambiguity as Q/A/P/E/X, scale process to task size, and verify before claiming. Injected into every session via a SessionStart hook.
★not rated 1 4mo agoA
tokens not measured
originalMIT
CEO-level strategic review for feature decisions. Challenges assumptions, applies strategy frameworks, and forces rigorous thinking before development begins.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Use QuantCoder from Claude Code to turn quantitative research papers into QuantConnect LEAN algorithm drafts, lint them, and optionally validate/backtest through QuantConnect.
★not rated 1 2mo agoA
tokens not measured
originalApache-2.0
Build production apps on SynapCores AIDB — an AI-native database that unifies SQL, vector search, a Cypher graph, LLM completion, an in-database agentic loop (AGENTRUN), durable agents, native image description, and MCP on one engine. Ships the build-with-synapcores skill, verified against engine v1.14.0-ce.
Scans your Claude Code plugin ecosystem and generates an ARCHITECTURE.md with Mermaid.js dependency graphs, collision reports, and ecosystem health scores.
★not rated 1 6mo agoA
tokens not measured
originalMIT
Auto-indexing for claude-context-mcp. Keeps your codebase index fresh on session start, after git operations, and on session end. Includes /insights skill for promoting memsearch patterns to auto-memory.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Distill technical discussions into compact, tagged decision entries with a live registry of open questions, all version-controlled in your repo and queryable by Claude.
★not rated 1 2mo agoA
tokens not measured
originalMIT
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: