joeblackwaslike

A large, auto-updating library of agent skills for Claude Code & Codex — Git/GitHub/Actions, Vercel, Serena, Dolt, DDD & SOLID, cross-platform plugin dev, docs tooling, and agentic best-practices. Every skill refreshes weekly from upstream docs.

1 plugin · joeblackwaslike/agent-skills

Claude Code plugin that intercepts automatic compaction and halts it, generating a structured session handoff instead of lossy compression.

1 plugin · joeblackwaslike/anti-compact

My curated marketplace and storefront for every plugin, skill, and tool I ship for Claude Code & Codex CLI — also home to the idea-nursery, where nascent macOS tools and automations incubate before earning their own repo.

10 plugins · joeblackwaslike/agent-marketplace

Reference implementation of Anthropic's 'Code execution with MCP.' Reuses Claude Code's own sandbox and config to keep intermediate tool output out of the context window on every workflow — up to 99% fewer tokens.

1 plugin · joeblackwaslike/mcp-exec

A Claude Code plugin that automatically captures coding mistakes and injects relevant lessons before tool calls — preventing the same mistakes from happening twice.

1 plugin · joeblackwaslike/lessons-learned

Discoverability and enrichment for Claude Code session transcripts — fixes a Claude Code bug that leaves ~90% of sessions undiscoverable, so past work can be found and reused across sessions.

1 plugin · joeblackwaslike/cc-recall

Tree/graph-based persistent context store for long-running agent sessions. Pairs with mcp-exec to return identifiers, snippets, and hints instead of full payloads — keeping raw output out of the window so agents work far longer before context fills.

1 plugin · joeblackwaslike/ctx-tree

Opinionated, strict TypeScript project scaffold that bakes in agentic-development best practices (Biome, ESLint strict, Vitest, Husky, CI) — so your AI writes better, more maintainable code that needs less review.

1 plugin · joeblackwaslike/spinup-ts