model-route

model-route is a command for Claude Code from liortesta/ClawdAgent. It costs 0 tokens per session (588 once invoked), scanned A, original, Apache-2.0.

A command that examines a task and recommends which available agent should handle it. Each agent has a fixed model tier, so the recommendation determines which model is used.

In plain words
What is it for?
Use it before starting work to select an agent for architecture, security, testing, performance, operations, documentation, code review, or simple task classification.
Why use it?
It removes guesswork when choosing between agents designed for deep reasoning, general development work, or quick simple tasks. This can help match the task to the intended cost and capability level.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/liortesta/clawdagent/model-route
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for model-route

README.md
[![agentmods](https://agentmods.dev/badge/commands/liortesta/clawdagent/model-route.svg)](https://agentmods.dev/commands/liortesta/clawdagent/model-route)
Your own site
<a href="https://agentmods.dev/commands/liortesta/clawdagent/model-route"><img src="https://agentmods.dev/badge/commands/liortesta/clawdagent/model-route.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 588 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00588
Opus 5 $0.00000 $0.00294
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 4d ago against content hash 615aa560e7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model-route scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/model-route.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Router — Agent & Model Recommendation

Analyze the current task and recommend which agent (and therefore which model tier) to use. Model is set PER AGENT in YAML frontmatter — it cannot change mid-session.

Agent → Model Mapping:

Opus Agents ($$$) — Deep Thinking

  • cto — Strategic decisions, architecture oversight, ADRs
  • architect — System design, API contracts, DB schemas
  • security-auditor — OWASP Top 10, CVE scanning, secrets detection
  • data-scientist — ML pipelines, feature engineering, data validation
  • meta-agent — Creates new agents on demand
  • swarm-leader — Coordinates agent teams, manages task boards
  • multi-ai-orchestrator — Routes tasks, coordinates cross-model workflows

Sonnet Agents ($$) — Balanced (DEFAULT)

  • qa-engineer — Tests, edge cases, 90%+ coverage
  • performance-engineer — Profiling, caching, bundle size
  • devops-engineer — CI/CD, Docker, K8s, monitoring
  • code-reviewer — Quality, readability, code smells
  • doc-writer — README, API docs, Mermaid diagrams

Haiku Agents ($) — Fast & Cheap

  • model-router — Task classification, agent recommendation

Recommendation Logic:

When receiving a task, recommend the appropriate agent:

IF task involves security/auth/payments → security-auditor (opus)
IF task involves architecture/design → architect or cto (opus)
IF task failed >2 times → escalate to opus agent
IF task is testing/QA → qa-engineer (sonnet)
IF task is simple fix (<20 lines) → direct edit, no agent needed
IF task is search/navigation → no agent needed (use Glob/Grep)
ELSE → sonnet agent matching the domain

Multi-Agent Orchestration:

For complex tasks, use multiple agents in sequence:

  1. model-router (haiku): Classify task, recommend agents
  2. Sonnet agent: Implement the solution
  3. Opus agent: Review the implementation (if critical)

Output:

TASK: [description]
CLASSIFICATION: [category]
RECOMMENDED AGENT: [agent name]
MODEL TIER: [opus/sonnet/haiku]
REASON: [why this agent]
ALTERNATIVE: [backup agent if first fails]

Read the full file on GitHub · 63 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 63 lines · 0 tokens per session scan A 615aa560e7c5

Subscribe to this mod's changes

model-route is a command published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 588 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.