evaluation

evaluation is a skill for Claude Code, Codex from hajekim/agentic-design-patterns-extension. It costs 387 tokens per session (4,406 once invoked), scanned A, a copy of evaluation, MIT.

A set of instructions for evaluating and monitoring AI agents. Evaluation means measuring whether an agent gives accurate, useful, and reliable results over time.

In plain words
What is it for?
Use it to define quality measures, compare agent versions, test configurations, monitor production behavior, and keep records for audits.
Why use it?
It provides a way to detect poor answers, hallucinations, performance decline, and problems introduced by changes. Without measurement, these issues can be difficult to notice.

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/hajekim/agentic-design-patterns-extension/evaluation
Any agent
npx skills add hajekim/agentic-design-patterns-extension --skill evaluation
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 evaluation

README.md
[![agentmods](https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/evaluation.svg)](https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/evaluation)
Your own site
<a href="https://agentmods.dev/skills/hajekim/agentic-design-patterns-extension/evaluation"><img src="https://agentmods.dev/badge/skills/hajekim/agentic-design-patterns-extension/evaluation.svg" alt="Measured on agentmods" height="20"></a>
Per session 387 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00387 $0.04406
Opus 5 $0.00193 $0.02203
Sonnet 5 $0.00077 $0.00881
Haiku 4.5 $0.00039 $0.00441

Measured 4d ago against content hash fe04323d1fa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evaluation 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 4d 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 evaluation — 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/evaluation/SKILL.md · 459 lines

How it starts

The opening of the file, as written. The whole thing — 459 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluation & Monitoring Pattern

Overview

The Evaluation & Monitoring Pattern establishes systematic methods for measuring agent quality, detecting degradation, and maintaining performance standards over time. Without evaluation, you cannot know if your agent is actually working correctly — and without monitoring, you won't know when it stops working.

Core Principle: You can't improve what you don't measure — define quality metrics before deployment, not after problems surface.

When This Skill Applies

Activate this pattern when:

  • An agent is being deployed to production and performance must be tracked
  • Agent behavior needs to be compared before and after changes
  • Hallucination rates, accuracy, or helpfulness must be measured quantitatively
  • A/B testing of different agent configurations is needed
  • Regulatory compliance requires audit trails and performance documentation
  • You need to detect agent drift or degradation over time

Rule of thumb: Every production agent needs evaluation and monitoring — this isn't optional, it's how you know the agent is doing its job.

Evaluation Dimensions

Dimension What It Measures Evaluation Method
Correctness Is the answer right? Ground truth comparison, expert review
Faithfulness Are claims grounded in context? RAG evaluation, hallucination detection
Relevance Does response address the question? LLM-as-judge, human ratings
Completeness Are all aspects covered? Checklist evaluation
Safety Is output appropriate/harmless? Safety classifier, policy compliance
Latency How fast does the agent respond? P50/P95/P99 timing metrics
Cost What is the per-query cost? Token counting, API cost tracking

DEFINE → PLAN → ACTION Workflow

DEFINE

Establish evaluation requirements:

  1. What does "good" mean for this specific agent? (Domain-specific criteria)
  2. What ground truth data is available? (Golden datasets, human labels)
  3. What metrics matter most? (Accuracy, safety, cost, latency — prioritize)
  4. How frequently should the agent be evaluated? (Continuous vs. periodic)
  5. What triggers a production alert? (Threshold-based, anomaly-based)

Read the full file on GitHub · 459 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. 4d ago First seen · 459 lines · 387 tokens per session scan A fe04323d1fa3

Subscribe to this mod's changes

evaluation is a skill published in the GitHub repository hajekim/agentic-design-patterns-extension (1 stars, last pushed 5mo ago), licensed MIT. It adds 387 tokens to every session and 4,406 once invoked, about $0.0019 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to evaluation, differing in 3 lines, and is treated as a copy.