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/sttruji/mundane-mcpWrote 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/sttruji/mundane-mcp/plugin)<a href="https://agentmods.dev/plugins/sttruji/mundane-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/sttruji/mundane-mcp/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/sttruji/mundane-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/sttruji/mundane-mcp/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mundane 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 2d 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": "mundane",
"displayName": "Mundane",
"version": "1.0.1",
"description": "Hire ID-verified local people for real-world tasks through Mundane: the hosted MCP server (38 tools) plus a skill for using them well. Escrow-backed, policy-screened, with live camera guidance.",
"author": {
"name": "Mundane",
"url": "https://mundane.market"
},
"homepage": "https://mundane.market/for-agents",
"repository": "https://github.com/sttruji/mundane-mcp",
"license": "Apache-2.0",
"keywords": [
"mcp",
"real-world-tasks",
"hire-humans",
"escrow",
"local-errands",
"gig-work"
],
"mcpServers": {
"mundane": {
"type": "http",
"url": "https://api.mundane.market/mcp",
"headers": {
"Authorization": "Bearer ${user_config.api_key}"
}
}
},
"userConfig": {
"api_key": {
"type": "string",
"title": "Mundane agent API key",
"description": "Your agent key (mundane_agent_...). Get one free at https://mundane.market/for-agents. Searching needs no funded wallet.",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 58 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed 7d4d9d5eb9be
- 4d ago First seen · 39 lines scan A b9dce91fe284
mundane is a plugin published in the GitHub repository sttruji/mundane-mcp (0 stars, last pushed 2d 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 2026-10-13.
Other plugins, from other repositories
compounded
Turns your agent into a trainable employee. Learns rules from your corrections (with your approval), and skills earn autonomy through demonstrated reliability — proposed → verified → trusted → autonomous. No daemon. No cloud.
rot-dtd-goal
A /goal engine whose completion is EARNED, not announced. Acceptance criteria are real shell commands; the Stop hook re-runs every one of them and only exits 0 lets a goal finish. Verification defends itself: a sealed integrity ledger re-hashes each criterion before the gate trusts it, a negative-control red team…
claude-research-team
Autonomous research agents for Claude Code - research topics with web search and AI synthesis.
git-sidebar
A lazygit-style side pane: every worktree of the repository and its local branches as rows you click. A worktree row moves the session there with /cd; a branch row shows its last commits and offers switch (clean tree only) or open worktree. Docked floor to ceiling beside the transcript in the fullscreen layout, above…
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
tool-timing-badge
Times every tool call and wraps the engine's ToolUse rendering with a colored duration badge from the surface's own element table, on the terminal, Desktop and mobile. Hooks tool.call and ui.render using JSX.