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/loncadev/baronWrote 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/loncadev/baron/claude-code)<a href="https://agentmods.dev/plugins/loncadev/baron/claude-code"><img src="https://agentmods.dev/badge/plugins/loncadev/baron/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/loncadev/baron/claude-code"><img src="https://agentmods.dev/badge/plugins/loncadev/baron/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
baron 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 10d 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": "baron",
"description": "Platform-agnostic work orchestration (issues, scm, ci, deploy, notify) for AI coding agents: drives work tracking, source control, pipelines, and notifications across providers via the Baron MCP server, with packaged workflows surfaced as recipe skills.",
"author": { "name": "Baron contributors" },
"license": "Apache-2.0",
"mcpServers": {
"baron": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@lonca/baron-mcp-server@latest"],
"env": { "BARON_PLUGIN_VERSION": "0.43.0" }
}
}
}
What it installs
The manifest is a name and a version. 10 skills travel with it, and installing the plugin installs all of them — 696 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.
- 10d ago Changed 4ea0fd9517c9
- 1mo ago Changed 1b245c496ace
- 1mo ago Changed 9fcf24e5417a
- 1mo ago First seen · 15 lines scan A 9e8ea25c67ae
baron is a plugin published in the GitHub repository loncadev/baron (1 stars, last pushed 10d 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 2026-08-31.
Other plugins, from other repositories
pm-autopilot
Put recurring rituals on autopilot: charter what to automate, schedule it on any runner (Claude Code routines, cron, n8n, GitHub Actions), and make every run delta-aware so it reports what changed, not what it already said. Ships with the recurring skills worth scheduling.
ados marketplace
Agentic Delivery OS - AI-powered software delivery system with 10-phase workflow.
auto-enrich
Auto-enrich user prompts with context for Jira tickets, GitHub PRs/issues/repos/files, GitLab issues/MRs/projects/files, and Sentry issues.
nyann
Project governance for Claude Code. Bootstrap and maintain git workflow, hooks, commits, releases, CI, docs, and repo health.
ai-sdlc-harness marketplace
AI-driven SDLC workflow harness — multi-agent dev with plan → code → review → test → PR.
gitlab
Connect Cursor to GitLab with the GitLab MCP server. Plan, track, and manage issues, merge requests, and pipelines from your editor.