agentsclimarketplace
Sign in

Subagent orchestration

Skill kpab/claude-fable-5-skills/skills/subagent-orchestration

Patterns for delegating work to parallel subagents with Claude Fable 5 — when to split tasks, async coordination, long-lived workers, and fresh-context verifiers. Use when designing multi-agent harnesses, when a large task has independent parts, when runs bottleneck on sequential steps, or when self-review keeps missing its own mistakes.From its SKILL.md

Install
npx -y skills add kpab/claude-fable-5-skills --skill subagent-orchestration

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.0 KB, 344 tokens by cl100k_base, as published. Nobody here has run it

Subagent Orchestration

Fable 5 dispatches and sustains parallel subagents far more dependably than prior models. Used well this cuts wall-clock time and improves verification quality; used badly it burns tokens on coordination overhead. The patterns:

When to delegate

Split out a subtask when it is (a) independent of your current working context, (b) large enough to amortize the handoff, and (c) specifiable in a few sentences plus file pointers. Don't delegate tightly coupled edits — coordination costs exceed parallelism gains.

Coordination

  • Launch independent subagents in the same turn and keep working while they run; don't block on the slowest one.
  • Intervene only on signal: a subagent off-track or missing context it can't discover itself.
  • Prefer long-lived subagents that carry context across related subtasks over respawning per subtask — repeated context loading is the dominant hidden cost.

Fresh-context verifiers

For checking finished work, a separate verifier subagent with a clean context outperforms self-critique: it can't share your blind spots because it doesn't share your assumptions. Give the verifier the specification and the output — not your reasoning — and have it report discrepancies against the spec at a defined cadence (every N components, every X hours) rather than once at the end.

Handoff template

A good subagent brief contains exactly: goal (one sentence), inputs (paths/data), definition of done (checkable), constraints (what not to touch), and where to write results. If you can't fill these in, the task isn't ready to delegate.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most agent orchestration skills give in 344 tokens

Counted across 848 of the 1,300 authors here whose files we hold, read 2026-09-06

  • Dispatch one agent per independent problem domainin 56 of 848, across 42 files
  • Run full test suite after integrationin 55 of 848, across 42 files
  • Verify fixes do not conflictin 40 of 848, across 32 files
  • Review each summary when agents returnin 40 of 848, across 31 files
  • Write a handoff document summarising the current conversationin 30 of 848, across 25 files
  • Reference existing artifacts by path or URLin 26 of 848, across 24 files
  • Give each agent a specific scopein 19 of 848, across 10 files
  • Give each agent a clear goalin 19 of 848, across 10 files
  • Include a suggested skills section in the documentin 18 of 848, across 16 files
  • Tailor the doc to the user argumentsin 18 of 848, across 15 files
  • Issue all subagent dispatches in the same responsein 17 of 848, across 11 files
  • Use git worktrees for isolationin 17 of 848, across 8 files

Said here and by no other author read

  • Launch independent subagents in the same turn
  • Prefer long-lived subagents over respawning per subtask
  • Use a fresh-context subagent to verify finished work
  • Provide specification and output to the verifier

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.