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/karanb192/claude-code-hooksWrote 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/karanb192/claude-code-hooks/cache-tax)<a href="https://agentmods.dev/plugins/karanb192/claude-code-hooks/cache-tax"><img src="https://agentmods.dev/badge/plugins/karanb192/claude-code-hooks/cache-tax.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
cache-tax 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 today.
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": "cache-tax",
"description": "The comeback price of a cold prompt cache, shown before you pay it. A UserPromptSubmit guard warns (or refuses once) when your next message will re-write a lapsed 1-hour cache at up to 80x the read rate, a SessionStart hook prices a stale resume, and the same script is a one-line status line segment with the minutes left and the cold-comeback cost.",
"version": "1.0.1",
"author": {
"name": "Karan Bansal",
"url": "https://github.com/karanb192"
},
"homepage": "https://github.com/karanb192/claude-code-hooks",
"license": "MIT",
"keywords": [
"claude-code",
"hooks",
"cost",
"prompt-cache",
"cache",
"observability",
"statusline",
"userpromptsubmit",
"sessionstart"
]
}
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.
- today First seen · 23 lines scan A ee10cc056abe
cache-tax is a plugin published in the GitHub repository karanb192/claude-code-hooks (503 stars, last pushed yesterday), 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 2026-09-07.
Other plugins, from other repositories
devops-tools
DevOps automation: ClickHouse, Doppler, MLflow, Cloudflare Workers, pueue orchestration, notifications, session recovery, MiniMax consensus analysis.
minimax
MiniMax M-series production wiring: OpenAI-compat quirks, hybrid prompt caching, Tier F quant agentic stack, model-upgrade detection. Distilled from a 41-iteration M2.7-highspeed exploration campaign.
quant-research
Quantitative research metrics: SOTA evaluation for range bars, Sharpe ratios with daily aggregation, ML prediction quality (IC, autocorrelation), crypto-specific considerations.
mql5
MQL5 development: indicator patterns, mql5.com article extraction, Python workspace, log reading.
LUXOR Database Pro
Professional database engineering skills covering PostgreSQL, SQLAlchemy, Alembic, pandas, Redis, vector databases, and database patterns.
LUXOR Data Engineering
Data engineering and ML skills covering Apache Airflow, Spark, Kafka, dbt, and MLOps workflows.