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/coltonbearden/carrelWrote 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/coltonbearden/carrel/carrel-agent)<a href="https://agentmods.dev/plugins/coltonbearden/carrel/carrel-agent"><img src="https://agentmods.dev/badge/plugins/coltonbearden/carrel/carrel-agent/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/coltonbearden/carrel/carrel-agent"><img src="https://agentmods.dev/badge/plugins/coltonbearden/carrel/carrel-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
carrel-agent 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": "carrel-agent",
"description": "Agentic file librarian for carrel desks: /index, /doctor, /catalog, /completion, a file-librarian agent, an agent-workflows skill, the carrel MCP server (14 tools + carrel:// resources), and a PostToolUse hook that re-indexes files Claude writes.",
"version": "0.5.0",
"author": { "name": "Colton Bearden" },
"license": "MIT",
"keywords": ["agent", "mcp", "index", "search", "catalog", "doctor", "hooks", "librarian"]
}
What it installs
The manifest is a name and a version. 1 skill, 4 commands, 1 agent, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 231 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 Changed b62d0cbdc6a5
- 1mo ago Changed 38551e4f925c
- 1mo ago Changed 4c036c666208
- 1mo ago Changed 416c066f1b95
- 1mo ago Changed 9115fa02a6fc
- 1mo ago First seen · 9 lines scan A 81fd2246b467
carrel-agent is a plugin published in the GitHub repository coltonbearden/carrel (2 stars, last pushed 3d 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
codebase-mapper
A self-maintaining codebase map: atomic docs Claude loads at the start of each session and keeps in sync as the code changes. Any stack; greenfield or existing.
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.
sessions
Skills for summarizing and recalling AI coding sessions across Claude Code, Codex, Pi, and OpenCode.
unforgit-claude-code-marketplace
Claude Code plugins for Unforgit persistent repository memory.
context-doctor
Cut your Claude Code bill, measured on your own sessions: /context-doctor:fix ranks every fix by what it would have saved you and applies the ones you choose (reversibly), /context-doctor:savings shows the dollars, and an every-prompt check names the waste.
context-guard
Context-budget guard for long Claude Code and Codex sessions: a Stop hook enforces a per-model checkpoint protocol (mechanical stub + budgeted memory-writer subagent on Claude; a direct stub-write instruction on Codex), and a SubagentStop tracker surfaces true session spend (main thread + subagents) on Claude. Default.