Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-09-17 · source-backed
v1.0.86-1 adds include-custom-instructions: true to custom agent frontmatter. Until now a custom agent ran without your repo conventions unless you duplicated them into the agent definition, which is exactly the kind of drift that produces two sources of truth. The same release fixes resumed sessions discarding marketplace plugins and skills after a reload when config read or validation failed, and changes the status row to say it's waiting for background shells rather than "Working" when a turn ends with a dev server attached.
Each link below shares sources, entities, or timing with this story.
Released September 4, custom agents can name several models in model, tried in order until one is available, with model-policy: required keeping model changes on that list. This is the first mainstream agent CLI where heterogeneous routing is config rather than a wrapper scrip...
The June 22 update lets you pick Claude from the agent picker after installing the Claude Code CLI and pointing Copilot at its path. Read the fine print: the Claude agent currently runs in bypass-permissions mode, auto-approving every file edit and tool call. That's a hard pas...
A spec is a press release until someone who didn't write it implements it. GitHub made Agent Plugins 1.0 generally available on August 12 across VS Code, Copilot CLI, the Copilot SDK, and the Copilot app on all plans. The spec, published August 6, was co-authored by AWS, Anysp...
Triple-stream retrieval (BM25 keyword, vector embeddings, knowledge-graph traversal) fused via Reciprocal Rank Fusion on the iii engine, with SQLite for state and an in-memory vector index, no external database. The economic claim: ~170K tokens/year (~$10) versus ~650K tokens...
MCP server exposing 150+ cybersecurity tools for AI agents: nmap, sqlmap, ffuf, and 147 others. Covers pentesting, vulnerability discovery, and bug bounty automation. Works with Claude, GPT, Copilot — any MCP-compatible agent. Docker support included. Add it to your MCP config...
43.3% on Frontier-Bench v0.1. Opus 4.8 scored 18.7%. That's not an incremental bump, that's the same benchmark with a different shape of answer. Anthropic released Claude Opus 5 on July 24 at $5/$25 per million input/output tokens, exactly half of Fable 5's $10/$50, while matc...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.