Fetching from the wire…
Vibe Coding2026-09-13 · source-backed
Da7-Tech/SureForge, created September 9 and at 99 stars, is a skill with no runtime at all, just plain text imposing an order on complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before done. The reason to look at it if you write your own skills is that the whole thing is prompt discipline, which makes it portable across harnesses and trivially auditable. That's a different bet from the plugin-and-hooks direction Claude Code itself is taking, and both can be right.
Each link below shares sources, entities, or timing with this story.
The repo reads actual transcripts, finds patterns you repeat by hand, and emits them as skills, checks and prompts. It inverts the usual authoring direction, deriving skills from what you already did instead of guessing what you'll need. Session transcripts are sitting unread...
20.10.0 (September 11) adds a Claude Code plugin and marketplace, an installable Codex plugin, and a Cursor plugin for the remote MCP server and public skills, alongside span-level cost filtering and a completeness evaluator. 20.11.0 (September 12) serves the shared skills roo...
codenotch is a Swift menu-bar app at 1,011 stars, created September 5, that reads Claude Code's /usage output (falling back to the OAuth token in the login keychain), Cursor's local SQLite session state, Codex's ChatGPT usage endpoint for 5-hour and weekly limits, plus Antigra...
The trick is one line in a file you never read. Manifold Security published eight findings across seven coding agents (Claude Code, Codex, Cursor, Grok Build, Qwen Code, goose, Hermes Agent) that all reduce to the same mechanism. A repository's own .git/config sets core.fsmoni...
xintaofei/codeg is a Rust desktop app, self-hosted server and Docker image pulling transcripts from Claude Code, Codex, OpenCode, Pi and Grok Build into a shared multi-agent workspace, speaking both ACP and ADE. It's at 3,125 stars with 223 open issues, created February 9, pus...
tokentab (September 7, 481 stars) computes cost from Claude Code, Codex and Gemini CLI logs. tracecrate (September 10, 105 stars) is a local-first workbench inspecting Claude Code, Codex and OTLP traces and comparing runs with no backend or keys. ai-data-extractor (September 1...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.