Pulse
What X is shipping with agents right now.
New skills, workflows, and tricks from people building with Claude Code, Codex, and Cursor. Our bots read X, keep the useful posts, and sum each one up in a line.
- posts tagged #subagents
- 4
- posts tagged #subagents
- builders
- 4
- builders
- topics
- 14
- topics

Piotr Miลkowski@piotr_minkowski
A drop-in .claude folder for Spring Boot projects: six specialist subagents (reviewer, security, DevOps and more) plus skills for JPA, testing, logging and modern Java, Apache-2.0.
๐ Claude Code Template v1.0 for Spring Boot is here! What's new? ๐น 6 rewritten agents ๐น 2 new skills + major improvements to existing ones ๐น Modern Spring Boot/Java patterns ๐น Better testing and security ๐ https://github.com/piomin/claude-ai-spring-boot #ClaudeCode #SpringBoot #Java #AI

CyrilXBT@cyrilXBT
A copy-paste settings.json plus two subagent files that split work by model: Opus plans, Sonnet codes, a Haiku scout searches files, and an Opus critic attacks the diff.
i can't comprehend why people run claude code on default settings one settings change and every model gets its own job: โ opus plans every task and advises when stuck โ sonnet 5.5 writes the actual code โ haiku handles every file search โ a critic agent tries to break your diff before you merge Opus thinks. The cheap models grind. paste this into claude code ๐ Add this to ~/.claude/settings.json. Keep every hook, permission and plugin I already have. Then create the two agent files below and show me the diff. ```json { "model": "opusplan", "advisorModel": "opus", "effortLevel": "medium", "modelSettings": { "claude-opus-5-5": { "effortLevel": "high" }, "claude-sonnet-5-5": { "effortLevel": "medium" } }, "env": { "CLAUDE_CODE_SUBAGENT_MODEL": "haiku" } } ``` ~/.claude/agents/scout.md ``` --- name: scout description: finds code fast. returns file paths and line numbers only. model: haiku tools: Read, Grep, Glob --- Locate exactly what was asked. Return file:line. No fixes. No opinions. ``` ~/.claude/agents/critic.md ``` --- name: critic description: reviews a diff or plan before any task is called done model: opus tools: Read, Grep, Bash --- Assume this is broken. Find how it fails. One line per issue, worst first. ```

Kaiju@kaijucode
A full Claude Code setup using only built-ins: CLAUDE.md, opusplan, Haiku search subagents, critic subagent, hooks, skills, worktrees, /schedule.
claude code basically runs my repo now, i just review and press enter... here's why: almost all of it is free config you set up once on day 1. here's my whole setup and what it costs: required (ships with claude code) > memory โ CLAUDE.md > models โ opusplan (opus plans, sonnet builds) > search โ haiku subagents for every file lookup > review โ a critic subagent before every merge > safety โ permissions in settings.json > undo โ plan mode + /rewind > context โ /clear between unrelated tasks optional (add when you need it) > automation โ hooks that format on every write > repeatable โ skills for the prompts you retype > parallel โ git worktrees > research โ /deep-research > escalation โ an opus advisor when you're stuck > scheduling โ /schedule routines the only thing on this list you need to pay for is your claude plan. everything else is included with claude code.

Thariq@trq212
Claude Code Desktop now knows its own capabilities, like spinning off subsessions. The team calls it almost a v2.
Claude Code Desktop is now so much aware of its own capabilities and how it can work with you, like spinning off subsessions. I think of this almost like a v2, so many small details went into make it great. https://t.co/dpgj4fd8sQ