Model Hierarchy

What it does

When your agent uses it

• Deciding which model to use for a task
• Spawning sub-agents
• Considering cost efficiency
• The current model feels like overkill for the task

Example prompts

• “model routing”
• “cost optimization”
• “which model”
• “/model-hierarchy”

Requirements

• Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Default to Tier 2 for interactive work
2. 2Suggest downgrade when doing routine work: "This is routine - I can handle this on a cheaper model or spawn a sub-agent."
3. 3Request upgrade when stuck: "This needs more reasoning power. Switching to [premium model]."

What it can do on your machine

Read from SKILL.md and the folder at commit 9095f83. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Model Hierarchy loads about 2.3k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 838 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~96

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zscole/model-hierarchy-skill at commit 9095f83, republished under its MIT licence (© zscole). 838 words, ~2,281 tokens.

name

model-hierarchy

description

Cost-optimize AI agent operations by routing tasks to appropriate models based on complexity. Use this skill when: (1) deciding which model to use for a task, (2) spawning sub-agents, (3) considering cost efficiency, (4) the current model feels like overkill for the task. Triggers: "model routing", "cost optimization", "which model", "too expensive", "spawn agent".

function selectModel(task):
    # Rule 1: Vision override (Tier 1/2 includes text-only models)
    if task.requiresImageInput or task.requiresVision:
        return VISION_CAPABLE_MODEL  # e.g. Kimi K2.5, GPT-4o, Gemini, Claude; do not use GLM 5 or other text-only
    
    # Rule 2: Escalation override
    if task.previousAttemptFailed:
        return nextTierUp(task.previousModel)
    
    # Rule 3: Explicit complexity signals
    if task.hasSignal("debug", "architect", "design", "security"):
        return TIER_3
    
    if task.hasSignal("write", "code", "summarize", "analyze"):
        return TIER_2
    
    # Rule 4: Default classification
    complexity = classifyTask(task)
    
    if complexity == ROUTINE:
        return TIER_1
    elif complexity == MODERATE:
        return TIER_2
    else:
        return TIER_3

# config.yml - set default model
model: anthropic/claude-sonnet-4

# In session, switch models
/model opus  # upgrade for complex task
/model deepseek  # downgrade for routine

# Spawn sub-agent on cheap model
sessions_spawn:
  task: "Fetch and parse these 50 URLs"
  model: deepseek

# Tier 1 with vision — Kimi K2.5 (multimodal)
model: openrouter/moonshotai/kimi-k2.5
# Heartbeats, cron, image-involving tasks: K2.5 handles text and vision.

# Tier 1 text-only — GLM 5 (no vision)
# model: openrouter/z-ai/glm-5  # exact ID TBD on OpenRouter Z.AI
# Routine text-only only; for image tasks use Kimi K2.5 or another vision-capable model.

# In CLAUDE.md or project instructions
When spawning background agents, use claude-3-haiku for:
- File operations
- Simple searches  
- Status checks

Reserve claude-sonnet-4 for:
- Code generation
- Analysis tasks

def get_model_for_task(task_description: str) -> str:
    routine_signals = ['read', 'fetch', 'check', 'list', 'format', 'status']
    complex_signals = ['debug', 'architect', 'design', 'security', 'why']
    
    desc_lower = task_description.lower()
    
    if any(signal in desc_lower for signal in complex_signals):
        return "claude-opus-4"
    elif any(signal in desc_lower for signal in routine_signals):
        return "deepseek-v3"
    else:
        return "claude-sonnet-4"

© zscole, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files in the repository root of zscole/model-hierarchy-skill.

• SKILL.md
• .gitignore
• LICENSE
• README.md
• examples/claude-code.md
• examples/openclaw.md
• pyproject.toml
• tests/conftest.py
• tests/scenarios.json
• tests/test_classification.py

Open the folder on GitHubat commit 9095f83