Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Subagent Fan-out — measured AI agent skill | DecimalAI

archive228/subagent-fanout

SkillScore55Maintained

Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.

agent-toolingby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-subagent-fanout/SKILL.md

decimalai skills pull archive228-subagent-fanout --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-subagent-fanout/SKILL.md https://app.decimal.ai/s/archive228-subagent-fanout/SKILL.md

Raw file: /s/archive228-subagent-fanout/SKILL.md ↗ · machine-readable summary at /s/archive228-subagent-fanout.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6h ago

—+1% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	2%	0%
case-06	✗→✓	▲ Improved	46%	0%
case-08	✗→✓	▲ Improved	159%	0%
case-09	✗→✓	▲ Improved	67%	0%
case-11	✗→✓	▲ Improved	-19%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/subagent-fanout/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Subagent Fan-out

One context loaded with ten jobs' worth of material is the exact shape that triggers context rot. Ten small contexts don't.

Spawn one subagent per independent unit (one file, one source, one check). Each gets a fresh context window.
An orchestrator synthesizes their results — it never does the per-unit work itself.
Give each worker a tight role and only the input it needs.
Use ONLY when the pieces are genuinely independent. Sequential dependencies stay in one chain.

Fan-out for breadth (research, multi-file edits, multi-source verification). Keep it serial when step N needs step N-1's output.

Want to see if archive228/subagent-fanout would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

archive228/subagent-fanout

SkillSafety

Source

Subagent Fan-out

Related skills