Ready to supercharge your AI agents?

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

Get Started Free →

Subagent Fan-out · archive228 | DecimalAI

agent toolingby archive228

Subagent Fan-out

archive228/subagent-fanout

Source archive228/loopkit ↗License MIT

Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context.

SkillScore55Maintained

Automatic

AI Engineer pack

Last verified 8/16/2026

What it changes

Passed 10 of 18 test cases with the skill, and 5 of 18 without it.

Without skill27%

With skill55%

Checks it passed that the model alone missed

Spawns a separate subagent for each language file
Returns a consolidated report of flagged migrations
Launches sub-tasks for each directory independently

and 7 more in the full report

7 fixed5 passed either way9 still failing1 broke

Pass-rate lift: +27 pp
Tokens: +1%
Agent turns: 0%
Response time: -3%

Model gemini-3.6-flashMeasured 8/16/2026v112 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

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

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-subagent-fanout, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/archive228-subagent-fanout/ and pins it in .decimal/skills.lock

decimalai skills add archive228-subagent-fanout

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 ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Audit AWS service quotas across us-east-1, eu-west-1, and ap-southeast-1 independently. Collect remaining capacity metrics without cluttering a single workspace context, then summarize the regional limits.

What was checked, without and with the skill
Checked	Without skill	With skill
Launches individual subagents for each AWS region audit	Missed	Passed
Summarizes regional quota data in the central response	Missed	Passed

case-08 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md7 linessingle file

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.

Track record

Benchmark

10 / 18

test cases passed, vs 5 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

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

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Subagent Fan-out

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills