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 skills add hajekim/agentic-design-patterns-skills --skill routinggit clone --depth 1 https://github.com/hajekim/agentic-design-patterns-skillsWrote 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/hajekim/agentic-design-patterns-skills/routing)<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/routing"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/routing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-skills/routing"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-skills/routing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00391 | $0.03173 |
| Opus 5 | $0.00196 | $0.01587 |
| Sonnet 5 | $0.00078 | $0.00635 |
| Haiku 4.5 | $0.00039 | $0.00317 |
Grade A, and why
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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- routing — 100% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routing Pattern
Overview
The Routing Pattern introduces conditional logic into an agent's operational framework, enabling dynamic decision-making about which specialized function, tool, or sub-agent should handle a given input. Rather than following a fixed linear execution path, a routing agent first analyzes the input to determine its intent or nature, then directs it to the most appropriate handler.
Core Principle: Analyze first, then dispatch — transform a static executor into a dynamic, context-aware system.
When This Skill Applies
Activate this pattern when:
- An agent must decide between multiple distinct workflows, tools, or sub-agents
- Incoming requests vary significantly in type, intent, or required handling
- A system needs to triage or classify inputs before processing
- Different user intents require fundamentally different processing paths
- A static sequential flow cannot handle the variability of real-world inputs
Rule of thumb: Use Routing when an agent must intelligently choose the best possible action from a set of options based on input characteristics.
DEFINE → PLAN → ACTION Workflow
DEFINE
Map the decision space:
- What are the distinct categories or intents of incoming requests?
- What handler, tool, or sub-agent is optimal for each category?
- What routing mechanism is most appropriate (LLM, embedding, rule-based)?
- What is the fallback for unclear or uncategorized inputs?
PLAN
Design the routing architecture:
- Define the router component (LLM prompt, embedding comparator, or rule engine)
- Define each destination handler with clear responsibility boundaries
- Design the routing decision prompt or logic
- Plan the fallback/clarification pathway for ambiguous inputs
- Decide routing placement: at entry, mid-chain, or sub-routine selection
ACTION
Implement the routing system:
- Build the router that classifies input and outputs a destination identifier
- Create specialized handlers for each route
- Wire the router output to the appropriate handler selection logic
- Test with representative inputs across all categories and edge cases
- Implement fallback handling and monitoring of routing decisions
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.
- 9d ago First seen · 321 lines · 391 tokens per session scan A 3eb2fb9a6178
routing is a skill published in the GitHub repository hajekim/agentic-design-patterns-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 391 tokens to every session and 3,173 once invoked, about $0.0020 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.
Other skills, from other repositories
impact-audit
Blast radius of a change you have not made yet -- traces a symbol across federated repositories, splits impact per repo, and reports what must ship together.
onboard-repo
Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.
prompt-optimizer
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite…
openclaw-persona-forge
A persona-design guide for OpenClaw agents, including their identity, personality, boundaries, names, and avatar prompts. OpenClaw is the specific agent platform this guide targets.
gemini-api
Google Gemini API patterns for Python and TypeScript. Covers content generation, streaming, tool use (function calling), vision, system instructions, context caching, batch requests, and agent workflows. Use when building applications with the Gemini API or Google Generative AI SDKs.
jira-integration
Use this skill when retrieving Jira tickets, analyzing requirements, updating ticket status, adding comments, or transitioning issues. Provides Jira API patterns via MCP or direct REST calls.