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.
npx skills add AnthonyAlcaraz/agentic-graph-rag-skills --skill context-failure-classifiergit clone --depth 1 https://github.com/AnthonyAlcaraz/agentic-graph-rag-skillsWrote 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.
[](https://agentmods.dev/skills/anthonyalcaraz/agentic-graph-rag-skills/context-failure-classifier)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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:
- Which agent-level failure mode is this? Action blindness, memory fragmentation, planning paralysis, context drift, or tool chaos.
- What is the architectural root cause? One of the five fatal flaws.
- 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
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.
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.
- 10d ago First seen · 130 lines · 157 tokens per session scan A 55a6639da20c
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.
Other skills, from other repositories
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
cvm-ai-doctor
A health-diagnosis workflow for servers, computers, virtual machines, and containers on Linux, macOS, or Windows.
ai-discover
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…
debug
Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.
nw-root-why
Root cause analysis and debugging.