13 posts tagged with "agents"

Eighteen agent definitions went from 8,798 lines to 664 and got better. What died: persona theater, THINK HARD, emoji. What survived, and why.

An agent that finished and one silently blocked look identical. The two delivery models, why self-reports are not evidence, and what to check.

A hidden Claude Code subagent watches another agent and reports drift. Observer agents: the enable flag, the digest, and the ObserverReport tool.

Claude Code sub-agents are now resumable via SendMessage and nest 5 levels deep. The persistent sub-agent pattern, field data, and the gotchas.

Claude Code subagents can now spawn their own subagents, capped at depth 5. How nesting works, the workflows it unlocks, and the token costs.

Claude Code's agent view ships May 2026 as a single dashboard for every running session. Dispatch tasks, peek status, reply inline.

Complete Claude Code agent teams workflow: structured planning, contract chains, and wave execution to ship production code with parallel agents.

Battle-tested agent team practices. Troubleshooting guide, limitations, plan mode behavior, and fixes from v2.1.33 to v2.1.45.

Stop your agent team lead from grabbing implementation work. Configure delegate mode, plan approval, hooks, and CLAUDE.md for teams.

Agent team examples and prompts for code review, debugging, full-stack features, architecture decisions, and marketing. Copy, paste, run.

Run multiple Claude sessions in parallel for multi-file refactors, test suites, and cross-domain work. Setup, patterns, and real examples.

Pair builder and validator agents using the Claude Code task system. Build-then-validate workflows with dependency chains.