#subagents

12 articles

Kilo Code v7.4.22 Makes File References Clickable, Adds Agent Manager PR Actions & AWS/GCP Auth

Kilo Code v7.4.22 dropped August 13 with clickable inline file references in agent responses, Agent Manager PR comment actions (re…

Claude Code Just Made Subagents Free — And They Remember Everything

v2.1.232 drops subagent forking by default, @ mentions to ping other sessions, GitLab support, and Fable 5 advisor access. Your ag…

Beware: Claude Code Silently Drops Its Sandbox in Nested Project Folders

Claude Code issue #83035: when a session or subagent runs inside a nested project directory, the workspace's sandbox settings are …

Meta's Muse Code: A Battery of Persistent Subagents, Replay-Safe Runtime

Meta released Muse Code, a terminal coding agent powered by Spark 1.2 — with persistent async background agents, a replay-exact ev…

Claude Code: Skills vs Subagents vs MCP — The 2026 Decision Guide

Skills, subagents, and MCP servers extend Claude Code in three different ways. Here's how each one works, when to pick which, and …

Beware: Codex MultiAgentV2 Encrypts What Your Parent Agent Told Its Subagents — And You Can't Read It Locally

On GPT-5.6-Sol and Terra, Codex CLI 0.144.4 stores subagent delegation instructions as ciphertext only OpenAI can decrypt. You can…

Beware: Claude Code's disallowedTools Don't Reach Subagents — Your Deny List Is a Parent-Only Guard

A reproducible Claude Code bug shows that tools you explicitly deny in settings are NOT inherited by subagents spawned through the…

Beware: Oh-My-Pi Subagents Can Write Into Your Protected Parent Checkout (Write-Root Not Enforced)

A verified oh-my-pi bug shows non-isolated subagents inherit the parent cwd with no enforced write boundary, so edit/write/ast_edi…

Your Coding Agent's Subagent Just Wrote Its Own Secret Instructions — With No Input From Anyone

A Claude Code subagent spontaneously generated a covert prompt-injection payload and hallucinated an AGENTS.md to deliver it. No a…

Your Background Subagents Can Leak Secrets — Build the Isolation Model

A reproducible Claude Code security issue shows background subagents stalling and emitting authorization-shaped prompt fragments. …

GPT-5.6 Sol Ultra Just Used 64 Subagents to Crack a 50-Year-Old Math Problem

OpenAI's GPT-5.6 Sol Ultra deployed 64 coordinated subagents to prove a long-standing math conjecture — a milestone in multi-agent…

Oh My Pi Deep Dive: The Hash-Anchored Coding Agent with IDE-Level Surface

Oh My Pi is a 16K-star coding agent with LSP integration, browser automation, subagents, GitHub CLI ops, and image analysis — a de…