context-failure-classifier

context-failure-classifier is a skill for Claude Code, Codex from AnthonyAlcaraz/agentic-graph-rag-skills. It costs 157 tokens per session (1,629 once invoked), scanned A, original, MIT.

A classifier that maps an agent's observed mistake to a named failure pattern, its underlying architectural flaw, and a possible graph-based remedy. It can also process lists of symptoms and rank remedies by how many problems they address.

In plain words
What is it for?
Use it for incident reviews, agent debugging, post-mortems, and deciding whether a problem involves memory, planning, context, actions, or tool coordination.
Why use it?
It turns vague reports such as forgotten information, broken dependencies, or incorrect tool choices into a structured diagnosis.

Skill for Claude CodeCodex

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

Good fit Use it for incident reviews, agent debugging, post-mortems, and deciding whether a problem involves memory, planning, context, actions, or tool coordination.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anthonyalcaraz/agentic-graph-rag-skills/context-failure-classifier
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 context-failure-classifier
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 context-failure-classifier

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/context-failure-classifier"><img src="https://agentmods.dev/badge/skills/anthonyalcaraz/agentic-graph-rag-skills/context-failure-classifier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,629 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 $0.00157 $0.01629
Opus 5 $0.00078 $0.00814
Sonnet 5 $0.00031 $0.00326
Haiku 4.5 $0.00016 $0.00163

Measured 10d ago against content hash 55a6639da20c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

context-failure-classifier 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/crisis/context-failure-classifier/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context-Failure-Mode Classifier

Overview

Ch1 argues the symptoms enterprises see — an agent that breaks dependencies, forgets, reverts to dead configs, can't connect facts, guesses the wrong API — are not independent bugs. They are the surface of five fatal flaws of naive vector RAG, and at the agent level each flaw "compounds into agent failure," "reinforcing others, creating a cascade of agent incompetence."

This skill maps a free-text symptom to that taxonomy. It answers three questions for each symptom:

  1. Which agent-level failure mode is this? Action blindness, memory fragmentation, planning paralysis, context drift, or tool chaos.
  2. What is the architectural root cause? One of the five fatal flaws.
  3. What cures it? The specific graph capability (entity relationships, evolving memory, temporal evolution, multi-hop reasoning, tool orchestration).

Batch mode reads a list of symptoms (e.g. a post-mortem's bullets) and returns a cure list ordered by how many symptoms each cure resolves — operationalizing Ch1's claim that closing one root flaw often relieves several symptoms because they cascade.

When to Use

  • Triaging why a deployed enterprise agent produces wrong / unsafe outputs
  • Turning a post-mortem's narrative into a prioritized architecture backlog
  • Deciding which graph capability to build first given observed failures
  • Teaching the difference between symptom (agent behavior) and root cause (architecture)

Phrases: "why did my agent break dependencies", "agent forgot context", "classify this failure", "agent reverted to old config", "agent picked the wrong tool", "what should we fix first".

When NOT to Use

  • General software bug triage — this taxonomy only covers retrieval/context failures
  • Model-quality complaints (hallucination from a weak model, refusals) — Ch1 is explicit the five flaws are architectural, not model quality
  • Latency / cost / infra incidents with no context-failure behavior

Process

Read the full file on GitHub · 130 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 · 130 lines · 157 tokens per session scan A 55a6639da20c

Subscribe to this mod's changes

context-failure-classifier is a skill published in the GitHub repository AnthonyAlcaraz/agentic-graph-rag-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 1,629 once invoked, about $0.0008 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