prioritization

prioritization is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 410 tokens per session (3,859 once invoked), scanned A, a copy of prioritization, MIT.

A pattern for ordering an agent’s work when several tasks compete for limited time or resources. It weighs importance, urgency, impact, deadlines, and interruptions.

In plain words
What is it for?
Use it for priority queues, deadline-aware scheduling, urgent task handling, workload management, and preemptive task execution.
Why use it?
It prevents an agent from handling requests only in arrival order when some work is more urgent or consequential. It also helps decide when higher-priority work should interrupt a lower-priority task.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for priority queues, deadline-aware scheduling, urgent task handling, workload management, and preemptive task execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hajekim/agentic-design-patterns-extension/prioritization
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.

Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill prioritization
Clone the repo
git clone --depth 1 https://github.com/hajekim/agentic-design-patterns-extension

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 prioritization

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/prioritization.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/prioritization)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/prioritization"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/prioritization.svg" alt="Measured on agentmods" height="20"></a>
Per session 410 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,859 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 $0.00410 $0.03859
Opus 5 $0.00205 $0.01929
Sonnet 5 $0.00082 $0.00772
Haiku 4.5 $0.00041 $0.00386

Measured 6d ago against content hash 1aa201a486e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

prioritization 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 6d 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.

Origin

This is a copy

100% identical to prioritization — 3 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/prioritization/SKILL.md · 407 lines

How it starts

The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prioritization Pattern

Overview

The Prioritization Pattern equips agents with the ability to intelligently order and schedule their work — managing multiple competing tasks by continuously evaluating their relative importance, urgency, and expected impact. Rather than executing tasks in arbitrary order, prioritizing agents allocate their limited attention and resources to what matters most.

Core Principle: Not all tasks are equal — do the right things in the right order, not just things in the order they arrived.

When This Skill Applies

Activate this pattern when:

  • Agents receive multiple concurrent requests that cannot all be handled immediately
  • Some tasks are time-sensitive (deadlines, SLAs, real-time alerts) while others can wait
  • Resources are limited and must be allocated to highest-value tasks first
  • Different users or workloads have different priority levels
  • Long-running tasks must be interruptible when higher-priority work arrives
  • The agent must balance urgent-but-less-important vs. important-but-not-urgent tasks

Rule of thumb: If the agent has more to do than time to do it — it needs prioritization.

Priority Frameworks

Eisenhower Matrix (Urgency × Importance)

                │  IMPORTANT  │ NOT IMPORTANT │
────────────────┼─────────────┼───────────────┤
   URGENT       │ Do First    │ Delegate/Auto │
────────────────┼─────────────┼───────────────┤
   NOT URGENT   │ Schedule    │ Eliminate     │
────────────────┴─────────────┴───────────────┘

Multi-Factor Priority Scoring

Priority = (Urgency × 0.4) + (Impact × 0.3) + (Effort × 0.2) + (Dependencies × 0.1)

WSJF (Weighted Shortest Job First)

WSJF = (Business Value + Time Criticality + Risk Reduction) / Job Size

Best for software/product backlogs — prioritizes small, high-value tasks.

DEFINE → PLAN → ACTION Workflow

DEFINE

Map prioritization requirements:

  1. What task types does the agent handle? (Categorize by domain)
  2. What dimensions determine priority? (Urgency, impact, effort, dependencies)
  3. What are the SLAs per task type? (Response time requirements)
  4. How dynamic is priority? (Static assignment vs. real-time re-evaluation)
  5. Can tasks be preempted? (Can high-priority work interrupt in-progress tasks?)

Read the full file on GitHub · 407 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. 6d ago First seen · 407 lines · 410 tokens per session scan A 1aa201a486e0

Subscribe to this mod's changes

prioritization is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 410 tokens to every session and 3,859 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to prioritization, differing in 3 lines, and is treated as a copy.