four-layer-eval-cascade

four-layer-eval-cascade is a skill for Claude Code, Codex from AnthonyAlcaraz/agentic-graph-rag-skills. It costs 211 tokens per session (3,270 once invoked), scanned A, original, MIT.

A step-by-step evaluation process for finding why an AI agent gave a bad answer, starting with grounding checks and moving to context, knowledge, and reasoning checks.

In plain words
What is it for?
Checking whether answers are supported by supplied information, whether the agent had enough context, and whether a failure came from knowledge or reasoning.
Why use it?
It helps separate made-up answers, missing information, incorrect knowledge, and reasoning mistakes before choosing a fix. The process stops at the first failing layer.

Skill for Claude CodeCodex

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

Good fit Checking whether answers are supported by supplied information, whether the agent had enough context, and whether a failure came from knowledge or reasoning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade
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 AnthonyAlcaraz/agentic-graph-rag-skills --skill four-layer-eval-cascade
Clone the repo
git clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skills

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 four-layer-eval-cascade

README.md
[![agentmods](https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade/github.svg)](https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade)
Your own site
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade/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.

agentmods 80×15 button for four-layer-eval-cascade

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/four-layer-eval-cascade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,270 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 original No closer match found 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 $0.00211 $0.03270
Opus 5 $0.00105 $0.01635
Sonnet 5 $0.00042 $0.00654
Haiku 4.5 $0.00021 $0.00327

Measured 10d ago against content hash d5decb58552d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

four-layer-eval-cascade 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (cli.py, lib.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/self-evolution/four-layer-eval-cascade/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Four-Layer Evaluation Cascade

Overview

The execution graph tells you what happened. This framework is the diagnostic engine that tells you why. It operates as a sequential filter, moving from the most general failure cause to the most specific, and it stops at the first layer that catches the failure. Each layer asks a progressively narrower question (Ch7 Figure 7-1):

  • Layer 0 (hallucination gate) gates on grounding. A lightweight NLI-style classifier scores whether the answer is grounded in the retrieved premise. The threshold is 0.85. It catches 60-70% of hallucinations at less than 5% of the compute of a full LLM judge call. Scores between 0.5 and 0.85 escalate to the full pipeline (the SLM-LLM flywheel); scores below 0.5 hard-block.
  • Layer 1 (context evaluator) asks: did the agent even possess the information it needed? A failure here is a knowledge-representation or retrieval failure, not a reasoning failure. The verdict is binary (sufficient or not) with a missing_information list (J1-style).
  • Layer 2 (cognitive fault isolator) splits a cognitive failure into two mutually exclusive categories. A KNOWLEDGE failure means coherent reasoning over wrong facts (low Knowledge Index). A REASONING failure means the right facts, badly connected (near-zero or negative InfoGain steps).
  • Layer 3 (TIR-Judge) verifies quantitative claims by executing code against the KG. Its reward is correctness * format * tool, multiplicative so a confidently wrong but well-formatted answer scores zero.

The output is a structured diagnostic report (the chapter's diagnostic-report example): it names the failure mode, locates it by node ID, and prescribes an intervention. That report is what drives the self-improvement engine.

The worked anchor is the DevOps premature-closure autopsy (the chapter's InfoGain-trace and diagnostic-report examples): sufficient context, Knowledge Index 0.91, InfoGain trace [0.34, 0.29, 0.22, 0.03, -0.01, 0.19], low-InfoGain steps [4, 5], fault at CausalAttributionNode, recommended intervention PROMPT_REFINEMENT.

Read the full file on GitHub · 191 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 191 lines · 211 tokens per session scan A d5decb58552d

Subscribe to this mod's changes

four-layer-eval-cascade is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 211 tokens to every session and 3,270 once invoked, about $0.0011 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.

Related

Other skills, from other repositories