Skip to content

Skill · pattern · orchestrator-workers

Orchestrator–workers

A parent decomposes work at runtime, spawns isolated workers, and synthesizes. Use for long-horizon research, DeerFlow/Deep Agents shape, or when subtasks are discovered during the run rather than at design time.

GET /api/canon/skills/orchestrator-workers?format=md

Anthropic catalog + Deep Agents / DeerFlow. Workers are context boundaries. Returns are documents, not transcripts.

When

Subtasks are not known up front. The parent must not drown in search hits.

Do

  1. 01

    Parent plans and synthesizes

    It does not read 40 hits. It writes briefs and reads 30-line summaries plus a notes path.

  2. 02

    Workers get a fresh window

    Reduced tools. No parent secrets. Caps on depth, breadth, time.

  3. 03

    Notes on disk

    Filesystem is source of truth. The window is a cache.

Don't

  • Dump worker transcripts into the parent.
  • Let workers spawn unbounded children.

Hard rules

  • A second agent is a context boundary, not a personality.
  • Return schema is part of the brief.

Worker brief

python
brief = {
    "goal": "Find prior art for feature flags in this repo.",
    "constraints": ["read-only", "no network", "10 minute cap"],
    "tools": ["grep", "read_file", "glob"],
    "return_schema": ["notes_path", "summary_30_lines", "open_questions"],
}
result = spawn_subagent(brief=brief, context="fresh", secrets=[], budget=Budget(max_steps=12))

Refuse

  • Shared mega-contextA crew sharing one bloated window. Specialists drown in each other's work.
  • Subagent inherits the parentNested loops get every tool and every secret. Isolation was theater.
  • Context hoardingRaw HTML, full CI logs, six PDFs, entire JSON envelopes stuffed 'just in case'. The goal is the first thing forgotten.

Load with this

Load next

Trigger tests

Should fire

  • Long-horizon research with subagents
  • DeerFlow-style orchestrator

Should not

  • Named three-stage pipeline