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/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/claude-eng-pack)<a href="https://agentmods.dev/plugins/atretyak1985/swarmery/claude-eng-pack"><img src="https://agentmods.dev/badge/plugins/atretyak1985/swarmery/claude-eng-pack.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
claude-eng-pack 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": "claude-eng-pack",
"description": "Claude-engineering domain pack: best-practice skills for building and auditing Claude agent systems — agent architecture, tool/MCP design, prompt engineering, Claude Code configuration, and context reliability. Opt-in; requires core.",
"version": "1.1.1",
"author": {
"name": "atretyak",
"email": "[email protected]"
}
}
What it installs
The manifest is a name and a version. 5 skills travel with it, and installing the plugin installs all of them — 620 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 36c7b91ab205
- 8d ago First seen · 10 lines scan A cf3c712fdcb8
claude-eng-pack is a plugin published in the GitHub repository atretyak1985/swarmery (4 stars, last pushed today), 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
claude-homelab marketplace
Plugin marketplace listing 26 plugins: homelab-core, overseerr-mcp, unraid-mcp, unifi-mcp, gotify-mcp.
axiom-git
Composes Conventional Commits messages with gitmoji from the staged diff, deciding type, scope, emoji, subject, and body, and gating on protected branches, staged secrets, and pre-commit hooks.
fakoli-plugin-critic
Five specialist critic agents for Claude Code plugin development — agent-critic (frontmatter/color/tools), skill-critic (lazy-loading/no-fuzzy-detection), hook-critic (contract-aware/${CLAUDEPLUGINROOT}), mcp-critic (schema/actor-validation), structure-critic (manifest/CHANGELOG/version-sync). Audit any plugin (your.
anvil-pulse
Live operator dashboard for long autonomous anvil runs: claims, phases, lease countdowns, event feed, and stuck-state detection served as a local web page, plus an optional Claude Code statusline segment.
cli-to-plugin
Convert any CLI tool into a self-contained Claude Code plugin by walking its --help tree and generating one skill per command group, plus optional LLM-proposed workflow meta-skills.
gate-router
Map changed Git files to local verification commands.