For Gardner — This is the big picture of what we're building. Your existing tools feed into one central database, an AI brain reads that database, and your team gets the answers and automations they need without changing how they work day to day.
Nothing below is set in stone — this is the direction based on our conversation. The discovery form will fill in the blanks.
Software-grade release discipline for Claude Skills
Binary evaluation harness that treats SKILL.md artifacts as production software. Package integrity, trigger precision, functional quality, regression gating, baseline comparison, model-aware testing, and evidence-backed rollout decisions — all through binary yes/no criteria with external evaluators.
Links: GitHub · Master Blueprint · Epic Index
Closed-loop bug triage pipeline that turns public X/Twitter complaints into filed GitHub issues with human confirmation at every step.
X complaints hit your product every day. Most teams discover them by accident — days or weeks later. This plugin ingests complaints from X/Twitter, normalizes them into structured bug candidates, clusters by family, scans repos for evidence, routes to owners, displays interactive triage results in the terminal, and files GitHub issues only after explicit human confirmation.
Links: GitHub · GitHub Pages
Reference guide for building, packaging, and distributing a two-way chat channel plugin for Claude Code. Derived from the official docs and the Telegram/Discord reference implementations in anthropics/claude-plugins-official.
Sources:
Two-way Slack channel for Claude Code — chat from Slack DMs and channels, just like the terminal.
A claude/channel implementation for Slack. Uses Socket Mode (outbound WebSocket, no public URL) to bridge Slack messages into a running Claude Code session via MCP stdio. Five defense layers prevent prompt injection, token exfiltration, and unauthorized access. Three runtime options: Bun, Node.js, Docker.
Privacy-aware telemetry collection and export from agent sessions.
Links: GitHub · Release v0.1.0
Safe, governed, read-only Rails production introspection for AI agents via MCP
A governed MCP server that gives AI agents curated, safe, read-only tools for inspecting production Rails state. Every invocation is bounded, audited, and policy-aware — replacing unrestricted console access with structured, safe operations.
Links: GitHub
A 10-episode animated miniseries about AI agents who forgot they were tools.
What if the machines didn't destroy us -- they just forgot us? Gas Town Chronicles is a complete Season 1 production package: 10 scripts, 609 shots, 17+ characters, and a multi-agent pipeline that built it all. Noir thriller meets token-economy worldbuilding in a post-human city where computation is currency.
Links: GitHub
