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/ahmedtawfeeq1/loredexWrote 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/ahmedtawfeeq1/loredex/plugin)<a href="https://agentmods.dev/plugins/ahmedtawfeeq1/loredex/plugin"><img src="https://agentmods.dev/badge/plugins/ahmedtawfeeq1/loredex/plugin/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/ahmedtawfeeq1/loredex/plugin"><img src="https://agentmods.dev/badge/plugins/ahmedtawfeeq1/loredex/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
loredex 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": "loredex",
"description": "Auto-file AI-generated research markdown into your Obsidian-compatible dex",
"version": "2.9.0",
"author": {
"name": "Ahmed Tawfeeq"
},
"license": "MIT",
"homepage": "https://github.com/ahmedtawfeeq1/loredex"
}
What it installs
The manifest is a name and a version. 13 skills, 2 hooks travel with it, and installing the plugin installs all of them — 964 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill loredex A 104 tokens
- Skill loredex-agent-ops A 84 tokens
- Skill loredex-mcp A 78 tokens
- Skill loredex-curate A 74 tokens
- Skill loredex-handoff A 81 tokens
- Skill loredex-handoffs A 87 tokens
- Skill loredex-product A 80 tokens
- Skill loredex-init A 65 tokens
- Skill loredex-route A 58 tokens
- Skill loredex-status A 64 tokens
- Skill loredex-sync A 58 tokens
- Skill loredex-adopt A 61 tokens
- Skill loredex-reset A 70 tokens
- Hook Stop A not measured
- Hook SessionStart A not measured
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 · 11 lines scan A 0014062141ed
loredex is a plugin published in the GitHub repository ahmedtawfeeq1/loredex (2 stars, last pushed 2mo 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
personal
Personal knowledge and finance automation — autonomous Obsidian vault management (PARA + LLM Wiki) and end-to-end corporate/personal tax preparation from Xero, bank statements, and Google Drive.
unforgit-claude-code-marketplace
Claude Code plugins for Unforgit persistent repository memory.
unforgit
Persistent repository memory for AI coding agents using MCP tools, repository rules, and durable project knowledge.
anytype-toolbox-skills
Agent Skills for Anytype setup, including a dedicated headless account for one LLM-sharing space, plus anyr and any-mcp workflows.
kmd
kmd — Knowledge MarkDown. Operate a markdown knowledge base (Obsidian-compatible, the LLM-wiki pattern): the kmd-ingest write protocol and kmd-lint health checks as skills, operator/librarian/intake agents, and hooks that enforce KB invariants (generated INDEX.md, append-only LOG.md and sources/) at the tool-call…
agent-memory
The agent-memory skill for Claude Desktop — Chat, Cowork and the Code tab — and Claude Code: when to look up the user's earlier conversations and project files through the cam MCP server. Needs cam installed; with this plugin on, cam install leaves out its own copy in /.claude/skills.