PreCompact
01Hook Claude Code
Runs before the context is compacted, running bd prime. From sfrangulov/minirag-mcp.
64 22d ago A
tokens not measured
copy · 100% MIT
SessionStart
02Hook Claude Code
Runs when a session starts, running bd prime. From sfrangulov/minirag-mcp.
64 22d ago A
tokens not measured
copy · 100% MIT
minirag-mcp
03Settings file Claude Code
Agent settings declaring 2 hook events (PreCompact, SessionStart).
64 22d ago A
tokens not measured
copy · 100% MIT
Instructions file CodexOpenCode
Instructions for sfrangulov/minirag-mcp, covering agent instructions, quick reference, non-interactive shell commands, force overwrite without prompting and for recursive operations.
64 22d ago C 973 tokens
copy · 72% MIT
Instructions file
Instructions for sfrangulov/minirag-mcp, covering project instructions for ai agents, beads issue tracker, quick reference, rules and session completion.
64 22d ago A 1,864 tokens
original MIT
minirag-mcp
06MCP server Claude CodeCodexCursor +2
Local-first RAG MCP server: hybrid search over your documents, fully local. Runs locally from the minirag-mcp Python package. Needs 13 environment variables to run.
64 22d ago A
tokens not measured
original MIT
PreCompact
07Hook Claude Code
Runs before the context is compacted, running bd prime. From sfrangulov/skill-graveyard.
10 1mo ago A
tokens not measured
copy · 100% MIT
SessionStart
08Hook Claude Code
Runs when a session starts, running bd prime. From sfrangulov/skill-graveyard.
10 1mo ago A
tokens not measured
copy · 100% MIT
Settings file Claude Code
Agent settings declaring 2 hook events (PreCompact, SessionStart).
10 1mo ago A
tokens not measured
copy · 100% MIT
Instructions file CodexOpenCode
Instructions for sfrangulov/skill-graveyard, covering agent instructions, quick reference, non-interactive shell commands, force overwrite without prompting and for recursive operations.
10 1mo ago C 973 tokens
copy · 72% MIT
Instructions file
Instructions for sfrangulov/skill-graveyard, covering claude.md, this repo is public, layout, development and tests.
10 1mo ago A 3,047 tokens
original MIT
Skill Claude CodeCodex
Audit which MCP server tools your Claude Code sessions actually invoke. Use when the user wants to find dead MCP servers (configured but never called), hallucinated MCP tool calls, or per-project MCP usage. Triggers on "which MCP servers don't I use?", "clean up MCP config", "remove unused MCP servers", "audit MCP…
10 1mo ago A 95 tokens
original MIT
Skill Claude CodeCodex
Audit which entries in your project's MEMORY.md Claude actually reads. Use when the user wants to find dead memory entries, broken pointers in MEMORY.md, orphan memory files, or surface entries that fall below the system-prompt truncation cutoff. Triggers on "audit MEMORY.md", "dead memory entries", "broken memory…
10 1mo ago A 103 tokens
original MIT
Skill Claude CodeCodex
Audit which Claude Code skills you actually invoke. Use when the user wants to find dead/unused skills, hallucinated skill invocations, per-project skill stats, or token cost of installed skill metadata. Triggers on "what skills don't I use?", "clean up my skills", "why didn't this skill work?", "audit skills". Runs…
10 1mo ago A 88 tokens
original MIT
Skill Claude CodeCodex
Distill a book, long-video transcript, podcast, course, or interview into a coherent set of executable agent skills. Use when the user asks to "distill this book into skills", "turn this video/podcast/course into agent skills", or wants the frameworks, principles, and methodologies in long-form content extracted into…
2 1mo ago A 96 tokens
original MIT
Skill Claude CodeCodex
A Russian-language framework for solving business and organizational problems through an eight-step consulting process. It treats the user as the decision-making partner and produces items such as a problem statement, issue tree, analysis, recommendations, and communication plan.
2 1mo ago A 298 tokens
original MIT
Skill Claude CodeCodex
Consulting Problem Solving Framework: An interactive, user-led approach to solving complex business and organizational problems using structured consulting methodology. You act as a consulting associate; the user acts as the consulting partner who drives decisions. Walks through problem definition, MECE structuring…
2 1mo ago A 288 tokens
original MIT
Skill Claude CodeCodex
End-to-end automated pipeline for recording polished 30-90s demo videos of React or HTML web apps. Universal keyboard-driven zoom hook with cinematic scenes → Playwright headless recording → Remotion overlay graphics (intro, callouts, count-up numbers, pulse highlights) → ElevenLabs voiceover with frame-perfect…
2 1mo ago A 190 tokens
original MIT
Skill Claude CodeCodex
Picks the next open-source product to ship when the goal is personal brand growth, not revenue. Trigger whenever the user is deciding which OSS tool, npm CLI, dev utility, or side project to build next — including phrases like "what should I open-source next", "picking my next product", "OSS portfolio strategy"…
2 1mo ago A 219 tokens
original MIT
Skill Claude CodeCodex
Disciplined multi-source research pipeline that produces a verifiable, citation-backed report — orchestrated subagents, source-discipline, content-addressed snapshots, a deterministic→judge verification funnel, and a mandatory adversarial fact-check pass. Use when a deep-research document (best-practices canon…
2 1mo ago A 107 tokens
original MIT
sfrangulov/claude-shared-memory-plugin
Skill Claude CodeCodex
A shared team memory skill backed by ChromaDB, a system for storing and searching text knowledge. It responds to requests about team knowledge, decisions, and shared memory.
2 6mo ago A 135 tokens
Skill Claude CodeCodex
A shared team memory skill using ChromaDB, a database for storing and searching information. It is intended for team knowledge, decisions, and shared memories.
2 6mo ago A 135 tokens
MCP server Claude CodeCodexCursor
MCP server "chroma-memory-mcp" as configured in sfrangulov/chroma-memory-mcp. Runs locally from the @sfrangulov/chroma-memory-mcp npm package.
2 6mo ago A
tokens not measured