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.
/plugin marketplace add AppsVortex/arnessnpx agentmods add plugins/appsvortex/arness/marketplacegit clone --depth 1 https://github.com/AppsVortex/arnessGrade A, and why
arn-marketplace 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://json.schemastore.org/claude-code-marketplace.json",
"name": "arn-marketplace",
"description": "The compound-engineering harness for Claude Code — durable artifacts hand off from discovery through deployment. Spark (idea), Code (build), Infra (ship).",
"version": "1.1.0",
"owner": {
"name": "AppsVortex",
"email": "[email protected]",
"url": "https://github.com/AppsVortex"
},
"plugins": [
{
"name": "arn-code",
"source": "./plugins/arn-code",
"description": "Artifact-driven pipeline — spec, plan, implement, review, ship, plus batch CVE scan & fix. Three ceremony tiers scale process to scope, from a one-file fix to a large refactor. 37 skills, 18 agents.",
"version": "3.8.0",
"author": {
"name": "Fryderyk Benigni",
"url": "https://github.com/fredcallagan"
},
"homepage": "https://arness.appsvortex.com/plugins/arn-code/",
"repository": "https://github.com/AppsVortex/arness",
"license": "MIT",
"keywords": [
"development",
"pipeline",
"code-review",
"pull-request",
"cve",
"security",
"sdlc",
"workflow",
"compound-engineering",
"harness-engineering",
"context-engineering",
"agentic-workflows"
],
"category": "development",
"tags": [
"development",
"code-review",
"automation"
]
},
{
"name": "arn-spark",
"source": "./plugins/arn-spark",
"description": "From raw idea to validated, feature-ready codebase — product discovery, adversarial spec review, brand naming, architecture vision, and interactive prototyping. 28 skills, 20 agents.",
"version": "2.4.0",
"author": {
"name": "Fryderyk Benigni",
"url": "https://github.com/fredcallagan"
},
"homepage": "https://arness.appsvortex.com/plugins/arn-spark/",
"repository": "https://github.com/ApWhat 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.
- yesterday First seen · 116 lines scan A 7b93155c02ed
arn-marketplace is a plugin published in the GitHub repository AppsVortex/arness (33 stars, last pushed 1mo ago), 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
cookbook
Train on Fireworks from your coding agent: managed SFT/DPO/ORPO/RFT plus Training API serverless and dedicated cookbook workflows.
agentic-awesome-skills
Plugin-safe Claude Code distribution of Agentic Awesome Skills with 2,039 supported skills.
ops
Structured non-code project management for Claude Code: planning, execution, knowledge persistence, and autonomous work loops for research, strategy, and content projects. 9 skills, 5 agents, 7 commands.
adapto
Operate Adapto CMS from your AI coding agent — a content studio: scaffold sites, build project context, and research, write, translate, and publish on-brand SEO content via the adapto CLI.
master-skills-ai-agent-builder
AI & Agents bundle — 388 curated skills (agents, ai-ml, prompt-engineering) for Claude Code, Codex & Antigravity.
deep-process-skills
Structured workflows that make LLMs think instead of just respond. Skills for verification, exploration, architecture, risk, feasibility, synthesis, and more.