Rules for running phone-first vibe coding with `Claude Code`

// related

• #0001

  #0001Agents & toolsClaude Code Releases29 minutes ago

  `Claude Code` `v2.1.146` tightens code review and background sessions

  50radar

  Claude CodeTerminal coding agent — automates code edits with Claude

  Small release, but it removes several annoying agent-run failures. Windows, MCP pagination, and multi-agent env handling all get more reliable.

  • —/simplify is now /code-review with optional effort levels like high, making review intent clearer in repeatable workflows.
  • —MCP resources/list, resources/templates/list, and prompts/list no longer drop results after page 1. Tooling backed by large MCP servers becomes safer.
  • —Windows fixes cover pwsh launch failures, terminal strobing, NTFS junction cleanup, and GNOME paste behavior. Cross-platform CLI friction drops.
  • —CLAUDE_CODE_SUBAGENT_MODEL now reaches child processes in multi-agent sessions. Model routing gets less brittle for delegated coding runs.
  • —Auto-updater retries transient network failures, and large diff rendering is faster. Not flashy, but daily-use reliability improved.

  Source: github.com/anthropics/claude-code/releases/tag/v2.1.146Read original →
• #0002

  #0002Agents & toolsGeekNews2 hours ago

  Google Cloud revamps agent development with `Antigravity 2.0`

  70radar

  AntigravityAgent dev tool — links local prototypes to cloud execution

  Google is packaging local prototyping and cloud deployment into one agent stack. If Managed Agents API removes hosting glue, it is worth tracking now.

  • —Antigravity 2.0 and Managed Agents API are framed as an integrated dev kit, not separate demos.
  • —The flow targets local prototyping first, then managed cloud execution. Less custom orchestration if the API is usable.
  • —The available text is short, so pricing, lock-in, and runtime limits remain unknown. Treat it as watchlist, not migration trigger.

  Source: news.hada.io/topic?id=29718Read original →
• #0003

  #0003Agents & toolsopencode_releases5 hours ago

  `opencode` `v1.15.6` adds TUI diff review and shell mode

  70radar

  opencodeOpen-source coding agent CLI — TUI-first workflow

  Change review now happens inside the TUI, and run prompts can drop into shell mode. This is a practical upgrade for terminal-first agent workflows.

  • —The TUI adds a diff viewer with auto-focus on the first file and collapsed single-child directories, cutting review friction before accepting edits.
  • —Run now gets shell mode and replaces subagent tabs with an on-demand picker, making agent sessions less crowded during longer tasks.
  • —Plugin failures are better isolated: file load errors and missing tool args no longer break the rest of plugin loading.
  • —v2 HTTP API now exposes structured public error schemas and preserves endpoint error responses in the OpenAPI spec.

  Source: github.com/anomalyco/opencode/releases/tag/v1.15.6Read original →