Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · claude-code

Orchestrate subagents at scale with dynamic workflows changed

workflows

Nearest release: v2.1.273, published 3 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+3added
Lines−3removed
From line 23 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits29to this page, all time

The whole hunk

from line 23, old and new numbered
/
lines
from line 23
2323| Scale | A few delegated tasks per turn | Same as subagents | A handful of long-running peers | Dozens to hundreds of agents per run |
2424| Interruption | Restarts the turn | Restarts the turn | Teammates keep running | Resumable in the same session |
2525 
26A workflow moves the plan into code. With subagents, skills, and agent teams, Claude is the orchestrator: it decides turn by turn what to spawn or assign next, and every result lands in a context window. A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.
26A workflow moves the plan into code. With subagents, skills, and agent teams, Claude is the orchestrator: it decides turn by turn what to spawn or assign next, and every result goes into a context window. A workflow script holds the loop, the branching, and the intermediate results itself, so Claude's context holds only the final answer.
2727 
2828Moving the plan into code also lets a workflow apply a repeatable quality pattern, not just run more agents: it can have independent agents adversarially review each other's findings before they're reported, or draft a plan from several angles and weigh them against each other, so you get a more trustworthy result than a single pass.
2929 
from line 57
5757 </Step>
5858 
5959 <Step title="Read the report">
60 When the run finishes, the report lands in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
60 When the run finishes, the report appears in your session. It cites the sources each claim came from, with claims that didn't survive cross-checking already filtered out.
6161 
6262 When the verifier agents can't check a claim, such as after a rate limit or API error, the report lists that claim as unverified instead of counting it as refuted.
6363 </Step>
from line 257
257257 
258258### Review every changed file and write one summary
259259 
260Run a reviewer per file, then hand all the findings to one agent that ranks and deduplicates them.
260Run a reviewer per file, then pass all the findings to one agent that ranks and deduplicates them.
261261 
262262```text wrap theme={null}
263263use a workflow to review every file changed in this PR for correctness issues, then merge the per-file findings into one ranked summary
Feedback