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/nitishagar/lumenWrote 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/nitishagar/lumen/plugin-lumen)<a href="https://agentmods.dev/plugins/nitishagar/lumen/plugin-lumen"><img src="https://agentmods.dev/badge/plugins/nitishagar/lumen/plugin-lumen/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/nitishagar/lumen/plugin-lumen"><img src="https://agentmods.dev/badge/plugins/nitishagar/lumen/plugin-lumen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
lumen 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 16d 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": "lumen",
"version": "0.3.0",
"description": "Honest, deterministic SEO audits — the lumen MCP server (5 tools) plus the seo-check skill that audits a site and fixes the top findings.",
"author": {
"name": "Nitish Agarwal"
},
"homepage": "https://github.com/nitishagar/lumen",
"license": "Apache-2.0",
"keywords": ["seo", "audit", "mcp"]
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 44 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.
- 16d ago First seen · 12 lines scan A 79bb302f472b
lumen is a plugin published in the GitHub repository nitishagar/lumen (0 stars, last pushed 6d ago), licensed Apache-2.0. 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 2026-09-30.
Other plugins, from other repositories
writing
Prose-quality skills: agent-style, remove-ai-patterns, and Jev-powered prose checks with bounded revision loops.
linearis
Agent skill for the linearis Linear.app CLI: preflight, discover-then-act usage protocol, JSON output, error envelopes and exit codes, ID resolution, discussions, files.
epic
3 commands + 25 auto-trigger skills + self-evolving agent harness. Less to remember, more automation.
titen-memory
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.
diffctx
Selects the minimum code an LLM needs to review a git diff.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.