Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
#ai-coding
318 posts
Agent skills for Spec Kit
When your AI agent needs an answer or approval, it pings you and waits. One-file Python CLI — works from Cursor, Claude Code, Codex, and any...
Agent skills for CodeAlive — semantic code search and AI-powered codebase answers. Works with Claude Code, Codex, Antigravity, Cursor, OpenC...
Self-improving AI brain for Claude Code & Desktop — 28 MCP tools, 253 skills, collective memory, project tracking, work logs. One server, al...
Multi-agent harness that runs Claude Code and Codex together as one system
Nine quality-canary skills for AI coding agents - code health, grounding, supply chain, resilience, drift & more. Cross-agent, consent-gated...
Product-side Spec-Driven Development framework — PRD, interactive prototype, DDD handoff, AI runtime governance, acceptance gates. L0-L3 tie...
Cheese your code 🧀 — high-quality results as easy as cheese. A portable, harness-agnostic Agent Skills toolkit.
Orchestrate parallel AI coding into reviewable PRs.
Memory washer/defragmenter for AI agent class-B memory - cleans the FAT, never the MEAT. Code-enforced zero-fact-loss gate, plan-sourced del...
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees,...