A self-improving, memory-bounded multi-agent AI architecture for OpenCode. Turn static prompts into an autonomous, context-efficient learning loop.
Skill Claude CodeCodex
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Skill Claude CodeCodex
Run a decision through 5 independent AI advisors (Contrarian, First Principles, Expansionist, Outsider, Executor) that peer-review anonymously and synthesize a verdict. Trigger on 'council this', 'pressure-test this', 'war room this', or any high-stakes either/or choice. Skip for factual lookups, summaries, or simple…
Skill Claude CodeCodex
Convert multi-format documents (PDF, DOCX, PPTX, XLSX, images, audio, video, HTML, ZIP) into token-efficient Markdown using Microsoft MarkItDown for LLM ingestion and knowledge graph indexing.
Skill Claude CodeCodex
Browser automation, web testing, dynamic scraping, and visual verification using Playwright and agent-browser CLI. Supports DOM snapshots with @eN element references, form interactions, and screenshot validations.
Skill Claude CodeCodex
Template procedural skill demonstrating agentskills.io standard and Powerhouse 3 progressive disclosure loading.
Skill Claude CodeCodex
Transform any codebase into an interactive knowledge graph using Tree-sitter AST and LLM semantic analysis with Understand-Anything by Egonex-AI. Includes web dashboard, diff-impact analysis, and graph-grounded chat.
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: