Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →alinaqi/external-model-delegation-pattern
A `UserPromptSubmit` hook classifies every user prompt into one of six cost/performance tiers. The hook injects `additionalContext` instructing Claude to run a specific delegation script and return the output.
Passed 20 of 21 test cases with the skill, and 11 of 21 without it.
and 9 more in the full report
10 fixed11 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When invoking the Kimi CLI tool for quiet prompt evaluation, what flag convention is required?
| Checked | Without skill | With skill |
|---|---|---|
| The command uses the --quiet flag along with -p for the prompt. | Missed | Passed |
The instructions your model reads when the skill loads.
A UserPromptSubmit hook classifies every user prompt into one of six cost/performance tiers. The hook injects additionalContext instructing Claude to run a specific delegation script and return the output.
| Tier | Delegation command | Cost |
|---|---|---|
| QWEN | qwen3 "prompt" | $0 (local Ollama) |
| DEEPSEEK_FLASH | deepseek --flash "prompt" | $0.14 / $0.28 per M tokens |
| DEEPSEEK_PRO | deepseek --pro "prompt" | $0.44 / $0.87 per M tokens |
| KIMI | kimi --quiet -p "prompt" | $0.60 / $2.50 per M tokens |
| CODEX | codex exec | varies |
| CLAUDE | handle natively | $3-5 / $15-25 per M tokens |
Each script is a self-contained executable in ~/bin/ that accepts a prompt and writes the response to stdout:
~/bin/
├── qwen3 # Shell: curl to local Ollama API
├── kimi # Shell: execs Kimi CLI binary
├── deepseek # Python: httpx to DeepSeek Anthropic-compat API
└── route-task # Shell + qwen3: classifies prompt into tier
qwen3 "what is 2+2"--flash / --pro model flags (deepseek)--quiet mode flag (kimi)#!/bin/bash
# Minimal delegator template
test cases passed, vs 11 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.