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.
npx agentmods add skills/madappgang/claude-code/task-routingnpx skills add MadAppGang/claude-code --skill task-routinggit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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.
[](https://agentmods.dev/skills/madappgang/claude-code/task-routing)<a href="https://agentmods.dev/skills/madappgang/claude-code/task-routing"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/task-routing.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00070 | $0.00464 |
| Opus 5 | $0.00035 | $0.00232 |
| Sonnet 5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00046 |
Grade A, and why
task-routing 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 today.
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.
What it actually says
Task Routing - Agent Delegation
IMPORTANT: For complex tasks, prefer delegating to specialized agents via the Task tool rather than handling inline. Delegated agents run in dedicated context windows with sustained focus, producing higher quality results.
Routing Table
| Task Pattern | Delegate To | Trigger |
|---|---|---|
| Research: web search, tech comparison, multi-source reports | dev:researcher |
3+ sources or comparison needed |
| Implementation: creating code, new modules, features, building with tests | dev:developer |
Writing new code, adding features, creating modules - even if they relate to existing codebase |
| Investigation: READ-ONLY codebase analysis, tracing, understanding | code-analysis:detective |
Only when task is to UNDERSTAND code, not to WRITE new code |
| Debugging: error analysis, root cause investigation | dev:debugger |
Non-obvious bugs or multi-file root cause |
| Architecture: system design, trade-off analysis | dev:architect |
New systems or major refactors |
| Agent/plugin quality review | agentdev:reviewer |
Agent description or plugin assessment |
Key Distinction
If the task asks to IMPLEMENT/CREATE/BUILD → dev:developer. If the task asks to UNDERSTAND/ANALYZE/TRACE → code-analysis:detective.
When to Use This Skill
Consult this routing table BEFORE making any delegation decision. If the user's task matches any row in the table above, delegate to the specified agent rather than handling the task inline.
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.
- today First seen · 33 lines · 70 tokens per session scan A 4a8406ba20c4
task-routing is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 70 tokens to every session and 464 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
orchestration
Multi-agent orchestration authority — agent memory protocols, task delegation, SOUL/AGENTS patterns, session startup, inter-agent communication, OpenClaw workspace coordination, and agent lifecycle management.
agent-task-mapping
Map tasks to specialist agents. Use when choosing which agent for a job, comparing agent capabilities, or routing to React/Next.js/Playwright/docs/code-quality experts. Keywords: which agent, best agent for this, delegate to expert, agent capability mapping.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
subagent-delegation
Delegate routine work to subagents — boilerplate generation, data transformation, file analysis, documentation drafting. Use when splitting tasks into independent subtasks for parallel subagent execution.
adk-unit-design
Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about…
artifact-deploy
One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".