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/g-akshay/ClaudeShrinkWrote 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/g-akshay/claudeshrink/marketplace)<a href="https://agentmods.dev/plugins/g-akshay/claudeshrink/marketplace"><img src="https://agentmods.dev/badge/plugins/g-akshay/claudeshrink/marketplace.svg" alt="Measured on agentmods" height="20"></a>Grade C, and why
ClaudeShrink marketplace scanned grade C with 2 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 8d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
"install": "curl -fsSL https://raw.githubusercontent.com/g-akshay/ClaudeShrink/main/install.sh | bash", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"install": "curl -fsSL https://raw.githubusercontent.com/g-akshay/ClaudeShrink/main/install.sh | bash", What it actually says
{
"name": "ClaudeShrink",
"slug": "claudeshrink",
"type": "skill",
"version": "1.0.0",
"description": "Automatically compress large natural text or log files before processing using LLMLingua to save tokens. Trigger when the user pastes massive text blobs, asks to analyze a large file (logs, docs, transcripts), or provides a prompt too large for the context window.",
"author": "Akshay Gundewar",
"repository": "https://github.com/g-akshay/ClaudeShrink",
"homepage": "https://github.com/g-akshay/ClaudeShrink",
"icon": "🗜️",
"tags": [
"compression",
"tokens",
"context-window",
"llmlingua",
"skills",
"ai-tool",
"claude-code",
"prompt-compression"
],
"skillFile": "SKILL.md",
"install": "curl -fsSL https://raw.githubusercontent.com/g-akshay/ClaudeShrink/main/install.sh | bash",
"requires": {
"python3": ">=3.9",
"git": "*"
},
"allowedTools": ["Bash"],
"platforms": ["macos", "linux"]
}
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.
- 8d ago First seen · 30 lines scan C a66dd344bcd3
ClaudeShrink marketplace is a plugin published in the GitHub repository g-akshay/ClaudeShrink (5 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 C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
linggen
Linggen for Claude Code — two local MCP servers, each tool served in one place: durable cross-host memory from ling-mem, browser control in your own Chrome and logged-in X reads from the Linggen engine. Per-turn memory recall built in, and /linggen:config points this host at a Linggen on another machine. Installs its…
linggen-memory marketplace
Linggen's plugin marketplace.
memory-kit
Persistent memory for your agent as plain files in your folder: a hot cache injected every session and held under three size caps, per-session handoffs, and promotion into knowledge articles and rules only on your yes. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second…
memory-kit
Persistent memory for Claude Code agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a…
membrain
Graph-based agent memory — search, trace, and manage what your agent knows.
capture
Capture session information into a staging file for later reflection and knowledge graph processing.