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/trevhud/roteWrote 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/trevhud/rote/plugin)<a href="https://agentmods.dev/plugins/trevhud/rote/plugin"><img src="https://agentmods.dev/badge/plugins/trevhud/rote/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/trevhud/rote/plugin"><img src="https://agentmods.dev/badge/plugins/trevhud/rote/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
rote 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 3d 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": "rote",
"displayName": "Rote",
"version": "0.16.0",
"description": "Compile an AI agent skill into a deterministic workflow for DBOS, Temporal, Cloudflare Workflows, Inngest, or plain Python with /rote:compile, fill in its emitted stub modules with /rote:implement, then trigger the deployed workflows from Claude over MCP with /rote:serve.",
"author": {
"name": "Trevor Hudson",
"email": "[email protected]",
"url": "https://github.com/trevhud"
},
"homepage": "https://roteskills.com",
"repository": "https://github.com/trevhud/rote",
"license": "Apache-2.0",
"keywords": [
"skills",
"workflow",
"compilation",
"temporal",
"cloudflare",
"dbos",
"inngest",
"python",
"typescript",
"durable-execution",
"mcp",
"claude",
"claude-code",
"agent-skills",
"token-cost",
"deterministic"
],
"documentationUrl": "https://github.com/trevhud/rote#readme",
"supportUrl": "https://github.com/trevhud/rote/issues"
}
What it installs
The manifest is a name and a version. 3 skills travel with it, and installing the plugin installs all of them — 390 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.
- 3d ago Changed a432b3b6b620
- 5d ago Changed 0421a98e80ba
- 6d ago Changed · +7 lines 375656999160
- 1mo ago Changed 537def2f5651
- 1mo ago First seen · 28 lines scan A 6112ecb44cc9
rote is a plugin published in the GitHub repository trevhud/rote (8 stars, last pushed yesterday), 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 2026-08-31.
Other plugins, from other repositories
roundtable
Your subagents as a pixel-art office. /roundtable:gif renders the session you are in as a timelapse GIF, /roundtable:watch opens the live office with a timeline you can rewind, and /roundtable:stats reports what your transcripts say about your fan-out. Read-only and local.
agent-teams
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams.
database-cloud-optimization
Database query optimization, cloud cost optimization, and scalability improvements.
distributed-debugging
Distributed system tracing and debugging across microservices.
claude-status-bar
Menu bar status indicator for Claude Code: animated spark, elapsed timer, and open/close lifecycle.
pr-provenance-stamp
Embeds a reviewer-facing provenance receipt into your PR body when Claude runs gh pr create (or glab mr create). A PostToolUse hook (async, zero added latency) records a per-session ledger: tool calls, agent-authored lines, and every test/typecheck command with its real exit code; a PreToolUse (Bash) hook then rewr.