resource-aware

resource-aware is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 408 tokens per session (3,557 once invoked), scanned A, a copy of resource-aware, MIT.

A pattern for making an AI agent aware of the resources it uses, including tokens, API requests, response time, and cost. It guides the agent in choosing an appropriate level of work for each task.

In plain words
What is it for?
Use it to manage model selection, context size, API-call counts, latency, quotas, and resource use in production or long-running tasks.
Why use it?
It helps keep agent operations within spending, speed, token, and rate limits instead of using the most expensive or largest option every time.

Skill for Claude CodeCodex

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

Good fit Use it to manage model selection, context size, API-call counts, latency, quotas, and resource use in production or long-running tasks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/resource-aware.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/resource-aware)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/resource-aware"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/resource-aware.svg" alt="Measured on agentmods" height="20"></a>
Per session 408 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,557 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 $0.00408 $0.03557
Opus 5 $0.00204 $0.01778
Sonnet 5 $0.00082 $0.00711
Haiku 4.5 $0.00041 $0.00356

Measured 7d ago against content hash 237a530f9803, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

resource-aware 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 7d 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 resource-aware — 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/resource-aware/SKILL.md · 378 lines

How it starts

The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resource-Aware Optimization Pattern

Overview

The Resource-Aware Optimization Pattern equips agents with awareness of the computational resources they consume — tokens, API calls, latency, and cost — and strategies to optimize their use. Rather than calling the most capable model for every request or retrieving maximum context every time, resource-aware agents make intelligent trade-offs to achieve goals within budget constraints.

Core Principle: Capability without efficiency is waste — match resource consumption to task requirements.

When This Skill Applies

Activate this pattern when:

  • API costs need to stay within budgets (production deployments at scale)
  • Latency requirements are strict (real-time user interactions)
  • Token limits constrain context window usage
  • Rate limits throttle request throughput
  • Different sub-tasks have vastly different complexity requirements
  • Long-running batch processes must manage resource consumption over time

Rule of thumb: If cost, latency, or quota is a constraint — build resource awareness in from the start, not as an afterthought.

Resource Dimensions

Resource Constraint Optimization Strategy
Tokens (input) Context window limit Summarize, truncate, selective retrieval
Tokens (output) Cost, latency Precise prompting, structured output
API calls Rate limits, cost Caching, batching, model selection
Latency User experience Async, streaming, parallel calls
Compute Server cost Efficient inference, model cascade

DEFINE → PLAN → ACTION Workflow

DEFINE

Map resource constraints:

  1. What are the token budget limits per session/task?
  2. What is the cost budget? (Per query, per day, per user)
  3. What are the latency requirements? (P50, P95, P99 targets)
  4. What rate limits apply? (Requests per minute, tokens per minute)
  5. Which sub-tasks are latency-sensitive vs. batch-OK?

PLAN

Design resource optimization architecture:

  1. Define model selection policy: capability vs. cost trade-off by task type
  2. Design caching strategy: what to cache, TTL, cache invalidation
  3. Plan context management: how to stay within token limits
  4. Design batching: group independent requests to amortize overhead
  5. Build monitoring: track resource usage against budgets in real-time

Read the full file on GitHub · 378 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. 7d ago First seen · 378 lines · 408 tokens per session scan A 237a530f9803

Subscribe to this mod's changes

resource-aware is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 408 tokens to every session and 3,557 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 resource-aware, differing in 3 lines, and is treated as a copy.