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/andisab/swe-marketplaceWrote 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/andisab/swe-marketplace/arch)<a href="https://agentmods.dev/plugins/andisab/swe-marketplace/arch"><img src="https://agentmods.dev/badge/plugins/andisab/swe-marketplace/arch/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/andisab/swe-marketplace/arch"><img src="https://agentmods.dev/badge/plugins/andisab/swe-marketplace/arch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
arch 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 today.
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": "arch",
"description": "Repository housekeeping agents: keep the CLAUDE.md context files Claude Code relies on accurate as a codebase evolves, and manage Docker and Make workflows.",
"version": "1.0.1",
"author": {
"name": "Andis A. Blukis",
"email": "[email protected]",
"url": "https://github.com/andisab"
},
"homepage": "https://github.com/andisab/swe-marketplace",
"repository": "https://github.com/andisab/swe-marketplace",
"license": "MIT",
"keywords": [
"architecture",
"orchestration",
"system-design",
"coordination",
"planning"
],
"agents": [
"./agents/arch-context-agent.md",
"./agents/build-orchestrator.md"
]
}
What it installs
The manifest is a name and a version. 2 agents travel with it, and installing the plugin installs all of them — 784 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.
- today Changed ad9d227dd323
- yesterday Changed ab3b71a626b9
- 1mo ago First seen · 25 lines scan A 7b0f0401987f
arch is a plugin published in the GitHub repository andisab/swe-marketplace (21 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
commander
Guided AI PM for Claude Code, running on The Fable Method — 12 enforceable gates so any model produces Fable-shaped results. 84 plugin skills (click-first /ccc- workflows, incl. /ccc-codex for the Codex CLI), 22 specialist sub-agents (architect, reviewer, debugger, designer, security-auditor…), 30 lifecycle hooks × 52.
commander-hud
Commander HUD: Fable state, running agents, tool-call budget and update pill above the prompt.
keep-alive
Prevents your machine from sleeping during Claude Code sessions (mirrors GitHub Copilot CLI /keep-alive).
matilha
You lead. Agents hunt. A cognitive + methodological harness for building complex AI-assisted projects — 11 phase-gated core skills, composition layer with plugin-namespace detection, SessionStart hook for cross-workspace activation, and 7 companion packs shipping 128 skills across UX, growth, agent architecture…
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.