context-degradation

context-degradation is a skill for Claude Code from guanyang/open-agent-hub. It costs 45 tokens per session (3,479 once invoked), scanned A, a copy of context-degradation, MIT.

A guide for diagnosing situations where an AI agent becomes less reliable as its conversation or input grows. It covers lost information, conflicting instructions, irrelevant context, and other context-related failures.

In plain words
What is it for?
Use it to investigate long-conversation failures, incorrect or irrelevant agent responses, context poisoning, lost-in-the-middle behavior, and production systems that handle large inputs.
Why use it?
It helps identify why an agent starts missing important details or producing confused answers, then treat the issue as a measurable engineering problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the open-agent-hub plugin — 102 skills, 3 commands, 5 agents, 6 MCP servers shipped together

Good fit Use it to investigate long-conversation failures, incorrect or irrelevant agent responses, context poisoning, lost-in-the-middle behavior, and production systems that handle large inputs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guanyang/open-agent-hub/context-degradation
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 guanyang/open-agent-hub --skill context-degradation
Clone the repo
git clone --depth 1 https://github.com/guanyang/open-agent-hub

Made for: Claude Code.

Or install open-agent-hub, the plugin that ships this one along with the rest of its 102 skills, 3 commands, 5 agents, 6 MCP servers.

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-degradation

README.md
[![agentmods](https://agentmods.dev/badge/skills/guanyang/open-agent-hub/context-degradation/github.svg)](https://agentmods.dev/skills/guanyang/open-agent-hub/context-degradation)
Your own site
<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/context-degradation"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/context-degradation/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-degradation

Your own site · 80×15
<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/context-degradation"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/context-degradation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,479 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 $0.00045 $0.03479
Opus 5 $0.00023 $0.01740
Sonnet 5 $0.00009 $0.00696
Haiku 4.5 $0.00005 $0.00348

Measured 10d ago against content hash 4e1896f641dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

context-degradation 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 1 executable file (scripts/degradation_detector.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.

Origin

This is a copy

100% identical to context-degradation — 0 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/context-degradation/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Degradation Patterns

Diagnose and fix context failures before they cascade. Context degradation is not binary — it is a continuum that manifests through five distinct, predictable patterns: lost-in-middle, poisoning, distraction, confusion, and clash. Each pattern has specific detection signals and mitigation strategies. Treat degradation as an engineering problem with measurable thresholds, not an unpredictable failure mode.

When to Activate

Activate this skill when:

  • Agent performance degrades unexpectedly during long conversations
  • Debugging cases where agents produce incorrect or irrelevant outputs
  • Designing systems that must handle large contexts reliably
  • Evaluating context engineering choices for production systems
  • Investigating "lost in middle" phenomena in agent outputs
  • Analyzing context-related failures in agent behavior

Do not activate this skill for adjacent work owned by other skills:

  • Explaining foundational context mechanics without an active failure: context-fundamentals.
  • Applying token-efficiency tactics after the failure pattern is known: context-optimization.
  • Designing a compression or handoff summary strategy: context-compression.
  • Persisting large outputs, logs, or scratch state outside the prompt: filesystem-context.

Core Concepts

Structure context placement around the attention U-curve: beginning and end positions receive reliable attention, while middle positions suffer materially reduced recall accuracy in long-context experiments (claim-context-degradation-lost-middle-ruler). This is not a model bug but a consequence of attention mechanics — the first token (often BOS) acts as an "attention sink" that absorbs disproportionate attention budget, leaving middle tokens under-attended as context grows.

Treat context poisoning as a circuit breaker problem. Once a hallucination, tool error, or incorrect retrieved fact enters context, it compounds through repeated self-reference. A poisoned goals section causes every downstream decision to reinforce incorrect assumptions. Detection requires tracking claim provenance; recovery requires truncating to before the poisoning point or restarting with verified-only context.

Read the full file on GitHub · 237 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 · 237 lines · 45 tokens per session scan A 4e1896f641dd

Subscribe to this mod's changes

context-degradation is a skill published in the GitHub repository guanyang/open-agent-hub (961 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 3,479 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to context-degradation, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

agent-expert-creation

Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.

majiayu000/claude-skill-registry · 43 tokens

agent-assistant

Agent assistance skill that provides stuck detection, memory management, and session learning capabilities for AI agents Trigger terms: agent stuck, loop detected, session memory, agent learning, condense memory, stuck detection, agent memory, session learnings, extraction Use when: User reports agent is stuck…

majiayu000/claude-skill-registry · 72 tokens

ac-memory-manager

Manage persistent memory for autonomous coding. Use when storing/retrieving knowledge, managing Graphiti integration, persisting learnings, or accessing episodic memory.

majiayu000/claude-skill-registry · 35 tokens

ac-knowledge-graph

Manage knowledge graph for autonomous coding. Use when storing relationships, querying connected knowledge, building project understanding, or maintaining semantic memory.

majiayu000/claude-skill-registry · 31 tokens

find-skills

Use when automatically discover, evaluate, and activate community skills when local skills don't cover user needs. Includes credibility scoring and safety checks for complete OpenClaw self-sufficiency.

oyi77/1ai-skills · 39 tokens

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions.

oyi77/1ai-skills · 29 tokens