task-router

task-router is a skill for Claude Code, Codex from arpitnath/claude-capsule-kit. It costs 43 tokens per session (2,143 once invoked), scanned A, original, MIT.

A decision guide for choosing how Claude should handle a task, such as working directly, using parallel work, or delegating to another agent. An agent is a specialized helper that can perform part of a coding task.

In plain words
What is it for?
Use it when starting a task, planning work across several files, choosing whether to delegate, or checking that your chosen approach fits the job.
Why use it?
It addresses uncertainty about the best approach, especially for large or complex work. The guide provides rules for deciding when specialized help is appropriate.

Skill for Claude CodeCodex

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 skills/arpitnath/claude-capsule-kit/task-router
Any agent
npx skills add arpitnath/claude-capsule-kit --skill task-router
Clone the repo
git clone --depth 1 https://github.com/arpitnath/claude-capsule-kit

Made for: Claude Code, Codex.

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/skills/arpitnath/claude-capsule-kit/task-router.svg)](https://agentmods.dev/skills/arpitnath/claude-capsule-kit/task-router)
Your own site
<a href="https://agentmods.dev/skills/arpitnath/claude-capsule-kit/task-router"><img src="https://agentmods.dev/badge/skills/arpitnath/claude-capsule-kit/task-router.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,143 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 5.1 $0.00043 $0.02143
Opus 5 $0.00022 $0.01071
Sonnet 5 $0.00009 $0.00429
Haiku 4.5 $0.00004 $0.00214

Measured 5d ago against content hash ab9048856592, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 5d 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.

skills/task-router/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Router Skill

This skill provides clear decision rules for choosing the optimal approach to any task.

Purpose

Problem: Claude has many tools (sub-agents, direct work, parallel calls) but no clear guidance on when to use each. Solution: Decision matrix with clear rules and examples.

When to Use

Activate this skill when:

  • Starting a new task and unsure of approach
  • Task seems complex (>30 min, >5 files)
  • User asks "what's the best way to do X?"
  • Need to validate chosen approach

Decision Matrix

🤖 Use agent-developer Sub-Agent

Trigger Conditions:

  • Building/creating mini-agents (Python with OpenAI Agents SDK)
  • Implementing executive agent configs (YAML)
  • Adding skills to skill registry
  • Writing job handlers for BullMQ
  • Integrating MCP servers
  • System Python Architecture tasks

Examples:

  • "Create a Slack notification mini-agent"
  • "Build job handler for experiment tracking"
  • "Add Google Docs skill to registry"

Why Delegate:

  • Specialized knowledge of agent patterns
  • Knows OpenAI Agents SDK deeply
  • Understands System Python Architecture
  • Has MCP integration best practices
  • 75% faster than manual implementation

How to Invoke:

Task tool with:
- subagent_type: "agent-developer"
- prompt: "Create [specific agent/handler] with [requirements]"

🔍 Use Explore Sub-Agent

Trigger Conditions:

  • Finding files by pattern/keyword
  • Understanding how a feature works
  • Locating implementation of functionality
  • Searching across multiple directories
  • Don't know exact file location

Examples:

  • "Where are errors from client handled?"
  • "Find all authentication-related code"
  • "How does the SSE streaming work?"

Why Delegate:

  • Multi-round investigation capability
  • Pattern matching across codebase
  • Faster than manual Grep/Glob
  • Systematic exploration approach

How to Invoke:

Task tool with:
- subagent_type: "Explore"
- prompt: "Find [what you're looking for]"
- Specify thoroughness: "quick", "medium", "very thorough"

Read the full file on GitHub · 391 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. 5d ago First seen · 391 lines · 43 tokens per session scan A ab9048856592

Subscribe to this mod's changes

task-router is a skill published in the GitHub repository arpitnath/claude-capsule-kit (90 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 2,143 once invoked, about $0.0002 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 2026-08-30.