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/stfade/mothWrote 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/stfade/moth/claude-code)<a href="https://agentmods.dev/plugins/stfade/moth/claude-code"><img src="https://agentmods.dev/badge/plugins/stfade/moth/claude-code/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/stfade/moth/claude-code"><img src="https://agentmods.dev/badge/plugins/stfade/moth/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
moth 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": "moth",
"version": "0.1.0",
"description": "Source-backed bug-fix analysis and verified local fix memory for AI coding agents.",
"author": {
"name": "Samet Taslioglu"
},
"license": "MIT",
"category": "development",
"keywords": ["mcp", "debugging", "bug-fix", "developer-tools", "claude-code"],
"skills": "./skills/",
"mcpServers": {
"moth": {
"command": "npx",
"args": ["-y", "@stfade/moth", "moth-mcp"]
}
}
}
What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 166 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 · 19 lines scan A 48697146844d
moth is a plugin published in the GitHub repository stfade/moth (2 stars, last pushed 5mo 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 2026-08-31.
Other plugins, from other repositories
codeindex
Skills that teach any agent to answer code questions structurally instead of reading whole files — symbol lookup, callers, imports and blast radius. Bundles the codeindex MCP server so install wires everything in one step.
visual-sentinel
Website monitoring from your AI assistant. Visual Sentinel catches pages that look broken even when the site is up. Five tools work with no account; the account tools need an API key (Business and Agency plans).
devcdp
Real Chrome DevTools access for Gemini CLI: console, network, DOM, source maps, breakpoints and live variables.
zapi-mcp
Zabbix API for Claude Code, via an API user. Investigate active problems, hosts, and item values, get a one-shot dailybrief health check, acknowledge problems, and open maintenance windows. Site-specific dailybrief categories (DHCP pool usage, SNAT usage, core-network, …) need a local ZABBIXCATEGORIESINI file that.
vibelens
Gives Claude eyes on localhost. Captures a screenshot, console/network errors and a token-optimized DOM snapshot of your dev server so UI bugs get fixed from evidence instead of guesswork.
python-code-validator
Checks every Python file Claude writes, before you read it: syntax, lint, types, an AST security policy and a credential scan, with the exact fix when there is one.