Plugin Claude Code
Plugin marketplace listing 1 plugin: tunaLlama.
44 1mo ago A
tokens not measured
original MIT
tunaLlama
02Plugin Claude Code
Delegate heavy code generation to a local LLM (Ollama / LM Studio). Search + memory layer + Codex CLI compatibility (one repo / two environments).
44 1mo ago A
tokens not measured
original MIT
tunallama
03MCP server Claude CodeCodexCursor +2
MCP server "tunallama" as configured in hang-in/tunaLlama. Launched with ${CLAUDE_PLUGIN_ROOT}/bin/tunallama-mcp.
44 1mo ago A
tokens not measured
original MIT
Agent
Subagent that delegates substantial code generation to the local LLM via tunaLlama and verifies the result. Use when the user wants you to write a non-trivial chunk of code and you want to save tokens. Reads markdown task specs (with optional Phase / Focus / Constraints) and runs a generate→review→fix→review loop.
44 1mo ago A 73 tokens
original MIT
SessionStart
05Hook
Runs when a session starts, executing session_start.py via python. From hang-in/tunaLlama.
44 1mo ago A
tokens not measured
copy · 59% MIT
PreToolUse
06Hook
Runs before the agent uses a tool for Read tool calls, executing pre_tool_use.py via python. From hang-in/tunaLlama.
44 1mo ago A
tokens not measured
original MIT
Skill Claude CodeCodex
Delegate suitable coding subtasks to a local/cloud LLM (Ollama / Ollama Cloud / LM Studio) via tunaLlama, like an architect delegating to a subagent. The local LLM has a smaller context window than Claude, so before delegating non-trivial work fetch relevant project context (state.md + past calls) and prepend it.…
44 1mo ago A 87 tokens
original MIT