claude

lackpy

Intent→sandboxed-program micro-inferencer (local model) + measured delegation guidance

3 on GitHubby Teague Sterlingv1.1.1MITupdated 4 days ago
/

Plugin lackpy from marketplace retritis in teaguesterling/retritis. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (2)

  • lackpy-delegation

    How to hand real work to a local small model through lackpy without wasting the round trip. Use when delegating to lackpy/Tiiny/Ollama — "have the local model fix this", "delegate this to lackpy", "offload this to the device", "run this on the small model" — and whenever a lackpy delegation returns

  • lackpy-workflow

    Local-model micro-inferencer — delegate natural-language intents to a sandboxed tool-composition program generator. Triggers on "delegate this to lackpy", "generate a program for...", "have lackpy figure out...", "run this query through the local model", "let the small model handle X". One lackpy `d

MCP servers (1)

  • lackpy

    runs: lackpyctl mcp serve

View source on GitHub

More from teaguesterling/retritis

All 10 plugins →

blq

claude

Build Log Query — stop copy-pasting terminal output into chat

1 skill · 1 MCP server · hooks

3

jetsam

claude

Git workflow accelerator — save, sync, ship without the five-step dance

1 skill · 1 MCP server · hooks

3

kibitzer

claude

Tool call observer — suggests structured alternatives when you reach for grep

1 skill · 1 MCP server · hooks

3

Cross-session memory, trust scoring, failure analysis

1 skill · hooks

3

fledgling

claude

DuckDB code analysis — definitions, callers, structure, similarity

1 skill · 1 MCP server

3

squackit

claude

Code intelligence MCP server — smart defaults, session caching, compound workflows

1 skill · 1 MCP server

3

Similar plugins

Agent runtimes — local WASM-sandboxed agents (rvagent) + Anthropic Claude Managed Agents (cloud); one interface, local-vs-cloud backends

5 skills · 2 commands · 9 agents

ruvnet/ruflo 81,589

fiftyone

claudecodex

Build high-quality datasets and computer vision models. Visualize datasets, analyze models, find duplicates, run inference, evaluate predictions, and develop custom plugins.

18 skills · 2 commands · 1 MCP server

anthropics/claude-plugins-official 47,076

Turn website visitor signals into pipeline with Leadfeeder: daily visitor briefs, visitor company research, buyer and contact discovery, personalised outreach drafts, and adding companies to your Leadfeeder lists, via the Leadfeeder connector. Requires a Leadfeeder account.

6 skills · 1 MCP server

anthropics/knowledge-work-plugins 35,601

context-mode

claudecodex

Context window saver for 10 coding agents. Local and free: sandboxed code execution, FTS5 search, session continuity.

3 skills · 1 MCP server

mksglu/context-mode 34,004

Answer questions about past agent runs from the recording, not from memory. Three read-only stdlib scripts over the session transcripts Claude Code and Codex already write: a finder that locates the run by repo, time window, touched file or command text; a timeline that numbers every step with its exit code, lists every file changed (flagging changes the agent never mentioned) and walks back from any step with each causal edge labelled recorded or inferred by a named rule; and a claim checker that tests a summary's claims (ran, passed, edited, not-edited, read) against the run and catches tests that passed before a later edit and exit codes that belong to the last command of a pipe. Secrets are always redacted. A UserPromptSubmit hook gives the agent this session's transcript path when a prompt asks about past work. Ships cs-run-forensics agent, /cs-run-forensics and /cs-check-claims commands and 3 cited references.

1 skill · 2 commands · 1 agent · hooks

alirezarezvani/claude-skills 29,725

Model optimization and quantization including Flash Attention, bitsandbytes, GPTQ, AWQ, GGUF, and HQQ. Use when reducing memory, accelerating inference, or quantizing models.

98 skills

Orchestra-Research/AI-Research-SKILLs 14,502

Maintain lackpy?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins10 plugins