{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-10-22-anthropic-fold-subagents-single-agent-loop-guide/","md":"https://postcutoff.com/e/2026-10-22-anthropic-fold-subagents-single-agent-loop-guide/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-10-22-anthropic-fold-subagents-single-agent-loop-guide","date":"2026-10-22","date_precision":"day","short_title":"Anthropic advises folding subagents into one agent loop with skills and tool search, and releases a reference kit to measure it","deck":null,"takeaway":null,"category":"agents","category_label":"Agents","importance":2,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"Claude: Building agents — When to fold subagents into your main agent loop (Oct 22)","url":"https://claude.com/resources/articles/building-agents-when-to-fold-subagents-into-your-main-agent-loop","type":"official","group":"primary","domain":"claude.com"},{"n":2,"title":"GitHub: anthropics/single-agent-loop-kit","url":"https://github.com/anthropics/single-agent-loop-kit","type":"code","group":"primary","domain":"github.com"}],"official":2,"filed":"2026-10-29","updated":"2026-10-29","orgs":["Anthropic"],"title":"Anthropic advises folding subagents into one agent loop with skills and tool search, and releases a reference kit to measure it","summary":"On Oct 22, 2026 Anthropic published \"Building agents: When to fold subagents into your main agent loop\" (Diane Sarkis), arguing that with newer models most router-plus-subagent systems should become one agent loop that loads skills and tools on demand, keeping a subagent only where evals show it pays. A companion repo, anthropics/single-agent-loop-kit (Apache-2.0), walks teams through measuring the change.","key_facts":["Article (claude.com, Oct 22, 2026, author Diane Sarkis): replace subagents where possible with one loop using progressive disclosure (skills for procedures, tool search for tools); keep a subagent only for measured context bloat, parallel work that benefits from fresh context, or tool-selection problems and conflicting instructions","Numbers cited: one customer's single loop ran about 2x faster than its multi-agent harness; Anthropic cut Claude Code's system prompt for more advanced models by over 80%; tool choice tends to degrade beyond 30-50 tool definitions in the prompt","Method: change one thing at a time against a task-completion eval, starting from about 10 golden examples, and run tasks more than once (in a sample support agent a failure appeared in one of two runs)","'Each new model lets you move more of the decision-making out of the harness and into the model itself.'","Kit: github.com/anthropics/single-agent-loop-kit (created Oct 15, Apache-2.0, ~420 stars by Oct 29), a reference implementation 'not maintained and not accepting contributions'; steps measure, combine, fold, with a runnable support-desk example (a router and six subagents)"],"key_numbers":[],"tags":["anthropic","claude","agents","multi-agent","subagents","skills","evals","engineering-guide"],"science":null,"body_md":"## What happened\n\nAnthropic's applied team published guidance that runs against the multi-agent fashion of 2025–26: as models improve, a single agent\nwith on-demand skills often beats an orchestrator with specialist subagents. The companion kit scores a system before and after\neach subagent is removed.\n\n## Why it matters\n\nIt is first-party advice from a frontier lab on agent architecture, and it explains why harnesses are getting thinner as models take\nover decisions that used to be hard-coded.","disputed":[],"related":[{"id":"2026-10-29-spawn-fable-agent-fleet-30x-payroll-tokens","url":"https://postcutoff.com/e/2026-10-29-spawn-fable-agent-fleet-30x-payroll-tokens/","date":"2026-10-29","date_precision":"day","short_title":"Spawn's founder says ten people and a fleet of Claude Fable agents ship ~108 changes an hour, spending 30x payroll on tokens","deck":null,"takeaway":"It is one of the most detailed first-hand accounts of a company run mostly by agents, published by the company itself.","category":"agents","category_label":"Agents","importance":3,"confidence":"medium","status":{"key":"partly","labels":["Partly confirmed"]},"sources":4,"official":2,"filed":"2026-10-29","updated":"2026-10-29","orgs":["Spawn","Anthropic"]}],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-10-29","type":"filed","text":"Created (news agent; a week after publication)"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-10-29","run":null,"sources_read":null,"updated":"2026-10-29","human_review":null,"version":{"date":"2026-10-29"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":144,"in_training_data":false},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":114,"in_training_data":false},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":205,"in_training_data":false},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":144,"in_training_data":false}],"short_url":null}