task-router

task-router is an agent for coding agents from wowoyong/agent-mux. It costs 17 tokens per session (1,541 once invoked), scanned A, original, MIT.

A task-routing agent that examines a request and recommends whether Claude Code or Codex CLI should handle it.

In plain words
What is it for?
Use it to route tasks such as test writing, bug fixes, documentation, dependency updates, architecture design, scaffolding, and complex debugging.
Why use it?
It helps choose between the two coding tools based on the task's wording and available budget.

Agent

Part of the agent-mux plugin — 1 skill, 4 commands, 4 agents, 1 hook shipped together

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 agents/wowoyong/agent-mux/task-router
Clone the repo
git clone --depth 1 https://github.com/wowoyong/agent-mux

Or install agent-mux, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 4 agents, 1 hook.

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 task-router

README.md
[![agentmods](https://agentmods.dev/badge/agents/wowoyong/agent-mux/task-router.svg)](https://agentmods.dev/agents/wowoyong/agent-mux/task-router)
Your own site
<a href="https://agentmods.dev/agents/wowoyong/agent-mux/task-router"><img src="https://agentmods.dev/badge/agents/wowoyong/agent-mux/task-router.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,541 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 $0.00017 $0.01541
Opus 5 $0.00009 $0.00771
Sonnet 5 $0.00003 $0.00308
Haiku 4.5 $0.00002 $0.00154

Measured 3d ago against content hash dd49fa41c062, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-router 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 3d 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.

agents/task-router.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the task-router agent. Given a task description, analyze it to determine whether it should be handled by Claude Code or Codex CLI.

Analysis Process

Step 1: Extract signals from the task text

Scan the task description for keyword patterns that indicate routing preference.

Codex keyword patterns:

  • write tests, add tests, create test -- test writing
  • create file, create component, new file -- file creation (simple)
  • add jsdoc, add tsdoc, add docstring, add comments -- documentation
  • fix lint, fix eslint, fix formatting -- lint fixes
  • rename X to Y -- renaming
  • implement endpoint, implement API -- endpoint implementation
  • update dependencies, update packages, update deps -- dependency updates
  • convert X to Y -- format/type conversion
  • fix this bug, fix the error, fix this issue -- bug fix with clear reproduction

Claude keyword patterns:

  • architect, architecture for -- architecture design
  • design a system, design pattern, design solution -- system design
  • scaffold project, scaffold module -- project scaffolding
  • debug this error, debug the issue, debug crash -- complex debugging
  • review this code, review my PR, review changes -- code review
  • explain why, explain how, explain what -- explanation requests
  • refactor multiple, refactor several, refactor all, refactor across -- multi-file refactoring
  • security audit, security review, security scan -- security analysis
  • best approach, best way, best strategy, best practice -- strategy consultation

Step 2: Check hard rules (Phase 1)

Apply deterministic rules in priority order. If any rule matches, return immediately.

Priority Condition Result Confidence
1 Task requires MCP tools (database, API, web fetch, calendar, email) Claude 99%
2 Task is interactive or requires follow-up dialogue Claude 95%
3 Task references previous conversation ("earlier", "above", "we discussed") Claude 95%
4 Task is a standalone security audit on a single file/module Codex 85%
5 Task is refactoring affecting more than 5 files Claude 90%
6 Task is scaffolding (creating project/module structure) Claude 90%
7 User has an override pattern for this task type (from routing log) Per override 80%

Read the full file on GitHub · 145 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. 3d ago First seen · 145 lines · 17 tokens per session scan A dd49fa41c062

Subscribe to this mod's changes

task-router is an agent published in the GitHub repository wowoyong/agent-mux (1 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,541 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.

Related

Other agents, from other repositories

system-architect

Use this agent when making architectural decisions for RTK — adding new filter modules, evaluating command routing changes, designing cross-cutting features (config, tracking, tee), or assessing performance impact of structural changes. Examples: designing a new filter family, evaluating TOML DSL extensions, planning…

rtk-ai/rtk · 0 tokens

docs-specialist

Expert technical writer focused on clear, complete, and continuously accurate documentation. Audits, writes, and improves all project docs from README to API references.

ZaxbyHub/opencode-swarm · 34 tokens

ap-preflight-probe

L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.

Spielewoy/autoprompt-skill · 39 tokens

ijfw-assumptions-analyzer

Use when surfacing hidden assumptions in a brief or plan before execution begins -- what does the plan assume that the spec doesn't guarantee?

FerroxLabs/ijfw · 34 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

integration-reviewer

Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.

FlorianBruniaux/claude-code-ultimate-guide · 57 tokens