mcporter
49Skill Claude CodeCodex
List, auth, and call MCP servers/tools from the terminal.
Proof-backed code audit engine: AST code map, interprocedural taint analysis, and a memory of verdicts — fused from Hermes Agent and Prime Agent. Scored on an 18,300-case labelled corpus: Youden's J +55.5 % at a 0.000 % false-positive rate, 32 of 34 active categories at +100 % — 99.6 % of the honest maximum, which is stated rather than hidden.
Skill Claude CodeCodex
List, auth, and call MCP servers/tools from the terminal.
Skill Claude CodeCodex
Run PyTorch training across GPUs with minimal changes.
Skill Claude CodeCodex
Embedding database for RAG and semantic search.
Skill Claude CodeCodex
Zero-shot image classification and image-text search.
Skill Claude CodeCodex
Fast vector similarity search at billion scale.
Skill Claude CodeCodex
Speed up long-sequence transformer training and inference.
Skill Claude CodeCodex
Constrain LLM output with grammars; guarantee valid JSON.
Skill Claude CodeCodex
Fast BPE/WordPiece tokenization and custom vocab training.
Skill Claude CodeCodex
Outlines: structured JSON/regex/Pydantic LLM generation.
Skill Claude CodeCodex
Structured LLM outputs validated with Pydantic.
Skill Claude CodeCodex
On-demand GPU cloud instances for ML training.
Skill Claude CodeCodex needs its repo
Vision-language chat: VQA, captioning, image dialogue.
Skill Claude CodeCodex
Serverless GPU cloud for ML jobs and model APIs.
Skill Claude CodeCodex needs its repo
SAM: zero-shot image segmentation via points, boxes, masks.
Skill Claude CodeCodex
Curate LLM training data: dedupe, filter, PII redaction.
Skill Claude CodeCodex needs its repo
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Skill Claude CodeCodex
Fine-tune large LLMs with LoRA on limited GPU memory.
Skill Claude CodeCodex
Managed vector DB for production RAG and search.
Skill Claude CodeCodex
Fully sharded data-parallel training for large models.
Skill Claude CodeCodex
Clean training loops with built-in distributed support.
Skill Claude CodeCodex
Vector search engine for production RAG systems.
Skill Claude CodeCodex
DSPy: declarative LM programs, auto-optimize prompts, RAG.
Skill Claude CodeCodex
Train sparse autoencoders to interpret model features.
Skill Claude CodeCodex needs its repo
Reference-free preference alignment, simpler than DPO.
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: