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.
git clone --depth 1 https://github.com/viktorbezdek/skillstackWrote 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/plugins/viktorbezdek/skillstack/context-degradation)<a href="https://agentmods.dev/plugins/viktorbezdek/skillstack/context-degradation"><img src="https://agentmods.dev/badge/plugins/viktorbezdek/skillstack/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.
<a href="https://agentmods.dev/plugins/viktorbezdek/skillstack/context-degradation"><img src="https://agentmods.dev/badge/plugins/viktorbezdek/skillstack/context-degradation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 1mo 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.
What it actually says
{
"name": "context-degradation",
"version": "1.0.11",
"description": "Patterns for recognizing and mitigating context failures in LLM agents. Covers lost-in-middle, context poisoning, distraction, confusion, clash, and model-agnostic degradation measurement.",
"author": {
"name": "Viktor Bezdek",
"url": "https://github.com/viktorbezdek"
},
"license": "MIT",
"repository": "https://github.com/viktorbezdek/skillstack/tree/main/context-degradation",
"keywords": [
"claude-code",
"skill",
"context-degradation",
"lost-in-middle",
"context-poisoning",
"attention-patterns"
]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 131 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 20 lines scan A 043258d35eac
context-degradation is a plugin published in the GitHub repository viktorbezdek/skillstack (14 stars, last pushed 4mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.
Other plugins, from other repositories
context-level
Gives Claude a tool that reads how much of the context window remains.
example-skills
Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling.
agent-tooling
Agent Tooling — Building the skills, hooks, commands, and plugins that agents run on.
agentic-awesome-skills
Plugin-safe Claude Code distribution of Agentic Awesome Skills with 2,590 supported skills.
claude-md-management
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
scout
Autonomous knowledge management and daily briefing system. Monitors your work tools (Slack, Calendar, Linear, GitHub, etc.), synthesizes findings into a persistent knowledge base with a formal ontology, and delivers daily action items — all running unattended via scheduled Claude Code sessions. Six session types…