Claude Code: Your Multi-Agent Dev Team.
Run a crew of Claude Code agents that write, review and ship in parallel. Ship in an afternoon what used to eat your week, then bring your teammates in and run it all from one shared workspace.
3 titles · 15 free guides
How to Make Two Claude Code Sessions Message Each Other
Hand work from one Claude Code session to another and have the second one start on its own, with nothing copied or pasted. One setting decides it, and left on the default it cost me three messages and about ninety minutes without a single error.
from: Claude Code Multiplayer
How to Debug a Multi-Agent Claude Code Run in One Command
Fix a broken multi-agent Claude Code run with one command that names the step that broke first. It reads one log line per tool call, and in the run shown here the crash was at step 4 while the cause sat two rows earlier, at step 2.
from: Claude Code Multiplayer
How to Check What Claude Code Still Knows After a Teammate Leaves
Put a shared Claude Code setup in front of a team and be able to show what the agent still knows when someone leaves. Two questions and two markers do it, and on my own run the fix I was sure of failed because the answer was still in git history, which sits on the same list as open sessions and saved approvals.
from: Claude Code Multiplayer
How to Share Your Claude Code Project With a Teammate
Bring a teammate onto your project mid-build and have their agent name the right plan without a call. Claude Code has no way to share a session, so we share one index file and a hook that blocks edits when two plans are marked ACTIVE, which is what keeps a 51-day-old handoff document from being read as today's plan.
from: Claude Code Multiplayer
How to Run 2 Claude Code Agents in One Repo Without Losing Work
Run two or more Claude Code agents in one repository and keep every agent's work. One table and one hook turn the second writer away before it touches the file, by name, and I built it after two agents reported the same file done and forty minutes of work was gone.
from: Claude Code Multiplayer
Give Your Claude Code Subagents Memory Without a Database
Full graph indexing costs about a thousand times what plain vector indexing costs, and frequently loses. Here is the three-layer file store that replaces it, with a pointer that walks any claim back to the sentence it came from.
from: Claude Code In Parallel
How to Stop a Claude Code Subagent From Faking a Test Pass
A verifier subagent will report a clean pass on tests it never executed unless you make the verdict a file it had to run something to produce. Mine did exactly that on 8 test cases, 0 of which ran, and the code being fine is the part that should worry you.
from: Claude Code In Parallel
How Do Claude Code Subagents Communicate? They Don't
There is no channel between subagents. If two of them have to agree on anything, the agreement lives in a file with exactly one owner per field, or it does not exist. Here is the file, and the race that eats it.
from: Claude Code In Parallel
Why You Shouldn't Use a Model to Merge Claude Code Subagent Results
A model asked to combine parallel agent findings is slow, gives different answers on different days, and can return a file path no searcher ever found. Four lines of shell do it deterministically and print a duplicate count that tells you how well you scoped the run.
from: Claude Code In Parallel
Claude Code Subagents in Parallel: Are They Actually Faster?
I timed the same job with one Claude Code agent and with three subagents in parallel, same repo, same afternoon. The graph lost twice. Here is how to measure your own floor and get a verdict on your own work.
from: Claude Code In Parallel
Claude Code Hooks: Wire a SubagentStop Hook
Wire a Claude Code SubagentStop hook to a log file and tail it live, so you catch hung, runaway, and suspiciously-fast subagents before they ship bad code.
from: Claude Code Subagents and Hooks
Run Claude Code Subagents in Parallel Without Clobbering
Multi-agent development with Claude Code clobbers files when workers share a checkout. Use git worktree isolation and claude --bg to fan out workers safely.
from: Claude Code Subagents and Hooks
Why Claude Code Subagents Burn So Many Tokens
Claude code subagents cost up to 85% of a heavy session. Route workers to cheaper models, audit the env var that undoes it, and cut the subagent bill 30%.
from: Claude Code Subagents and Hooks
Tool, Skill, or Subagent? The Claude Code Decision
Stop defaulting to a subagent. A four-axis Claude Code framework routes logic to an inline prompt, a tool call, a skill, or a subagent by cold-start cost.
from: Claude Code Subagents and Hooks
Read them in this order. Each one assumes the one before it.
Claude Code Subagents and Hooks
A planner-coder-reviewer stack, five hooks, worktree isolation, and cost routing that cuts the token bill 30%
Claude Code In Parallel
Twelve working graph systems on your own repo, a real cost number per run, and one packaged as a client deliverable
Claude Code Multiplayer
One shared workspace with an owner on every file, a proof gate neither agent controls, and a run priced to the cent
These titles sit on paths that tells you which three to buy first.