Mallikarjun H T’s MIT Claude Code plugin Agentic-SDD walks a feature through require→plan→analyze→implement→verify→fix, gated by on-disk status.json instead of chat memory, with an 18-agent specialist roster and a vendored Lucene search engine so grounding doesn’t depend on another MCP.
ssapable’s MIT MCP (plus Claude Code plugin) stores approve/edit/reject decisions in local PGlite+pgvector and injects the closest past corrections before the next draft—so style fixes don’t die with the chat. Install via /plugin or claude mcp add ; hooks cover SessionStart and UserPromptSubmit when tool calls alone aren’t enough…
Hao Li’s open source mcp lint audits an MCP tools/list for vague names, missing descriptions, unpaginated lists, and destructive tools without confirm hints—scoring each tool out of 100 with a CI fail under gate. Stdlib only Python (MIT), sibling to mcp tax’s token cost auditor; repo at github.com/hahahahahahahahah6/mcp lint…
September’s VS Code Copilot releases (1.136–1.140) add preview automations that run agent tasks hourly/daily/weekly, agent merge that works review feedback, failed checks, and conflicts toward merge, and PR creation from Copilot, Claude, or Codex sessions—plus Dev Container sessions from the Agents window…
OpenAI’s MCP Extensions let plugins hook into ChatGPT surfaces—sidebar apps, conversation panels, file viewers/editors, composer mentions, deep links, and rich forms—via TypeScript/Python SDKs; Bits & Bolts is the kitchen sink demo, with Canva, Figma, and Adobe already shipping examples. Web extensions are coming soon to Free/Go; composer mentions stay desktop only…
Anthropic’s Code Review (research preview, Team/Enterprise) dispatches multi agent reviewers on GitHub PRs—parallel bug hunt, false positive filtering, severity ranking—then posts an overview plus inline comments; it never approves. Internally, substantive PR comments rose from 16% to 54%; reviews average $15–25 in token usage…
Spotted something we missed? Start a thread.
