humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Manage webhook subscriptions — register, verify, rotate, and monitor webhook endpoints for external service integrations.
Drewgent configuration for opencode — agent profiles, skills, scripts, and tooling
This repository also configures its own agents. See what opencode-drewgent tells them →
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Manage webhook subscriptions — register, verify, rotate, and monitor webhook endpoints for external service integrations.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
WordPress CMS setup on Docker + Blocksy theme + MCP integration for autonomous content publishing.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
WordPress on Docker (colima) with Blocksy theme, custom fonts, MCP server for AI agent integration.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
A troubleshooting guide for deploying websites to Cloudflare Pages with Wrangler, Cloudflare's command-line deployment tool. It covers account-selection, authentication, and configuration errors.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
A procedure for checking whether files and folders mentioned in an agent’s memory or notes actually exist on disk.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
A Flask web server that displays a kanban board, a visual task board with columns such as To Do, In Progress, Blocked, and Completed. It includes live updates, drag-and-drop cards, and a mobile layout.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
A troubleshooting guide for a kanban dispatcher, the background process that moves or reclaims tasks on a kanban board. It checks why scheduled runs stop or stuck tasks remain in progress.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
A setup guide for adding Korean online payments to a Cloudflare Workers web app using PortOne and payment providers such as KG Inicis, Kakao Pay, and Toss Payments.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
⚠️ DEPRECATED — gbrain replaced by SQLite FTS5 + Ollama embeddings (2026-07-05). Use recall()/remember() tools instead.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex needs its repo
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament…
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex needs its repo
SAM: zero-shot image segmentation via points, boxes, masks.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.
humanerd-drew/opencode-drewgent
Skill Claude CodeCodex needs its repo
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
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: