Sub-skill of agent-usage-optimizer: Complexity Tier \u2192 Model Mapping.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add vamseeachanta/workspace-hub --skill complexity-tier-model-mapping --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Complexity Tier Model Mapping?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/vamseeachanta-complexity-tier-model-mapping-workspace-hub)More formats (shields.io, HTML) on the badges page.
---
name: agent-usage-optimizer-complexity-tier-model-mapping
description: "Sub-skill of agent-usage-optimizer: Complexity Tier \u2192 Model Mapping."
version: 1.0.0
category: ai
type: reference
scripts_exempt: true
---
# Complexity Tier → Model Mapping
## Complexity Tier → Model Mapping
Use this alongside Route mapping when task nature is clear:
| Complexity tier | Keywords | Recommended model |
|----------------|----------|------------------|
| `routine` | format, rename, config, scaffold, update-doc, copy | Claude Haiku |
| `standard` | implement, review, test, fix, migrate, document | Claude Sonnet |
| `complex` | architecture, design, cross-repo, security, compound | Claude Opus |
**Key insight**: the gap between theoretical and observed exposure is an implementation gap —
not a capability gap. Routing routine tasks to cheaper models closes this gap for our workflow.
See WRK-5002 to automate tier detection in `task_classifier.sh`.
---
*Use this skill before any multi-item work session or when quota is a concern.*
*Related: `ai/optimization/model-selection`, `ai/optimization/usage-optimization`*
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
一个全面的 Claude Code 会话验证系统。
Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
