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/openshift-eng/ai-helpersWrote 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/openshift-eng/ai-helpers/marketplace)<a href="https://agentmods.dev/plugins/openshift-eng/ai-helpers/marketplace"><img src="https://agentmods.dev/badge/plugins/openshift-eng/ai-helpers/marketplace/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/openshift-eng/ai-helpers/marketplace"><img src="https://agentmods.dev/badge/plugins/openshift-eng/ai-helpers/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ai-helpers 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 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.
How it starts
The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "ai-helpers",
"owner": {
"name": "openshift-eng"
},
"plugins": [
{
"name": "gopls-lsp",
"source": {
"source": "github",
"repo": "anthropics/claude-plugins-official",
"path": "plugins/gopls-lsp"
},
"description": "Go language server for code intelligence and refactoring",
"version": "1.0.0",
"category": "development",
"keywords": [
"go",
"gopls",
"lsp"
]
},
{
"name": "prodsec-skills",
"source": {
"source": "github",
"repo": "RedHatProductSecurity/prodsec-skills"
},
"description": "Security guidance skills for AI coding assistants",
"version": "1.0.0",
"category": "security",
"keywords": [
"security",
"prodsec"
]
},
{
"name": "patternfly",
"source": {
"source": "github",
"repo": "rh-uxd/ai-helpers",
"path": "plugins/patternfly"
},
"description": "PatternFly development tools from the UXD team \u2014 component scaffolding, design guidance, auditing, migration, test generation, and an MCP server.",
"category": "development",
"keywords": [
"patternfly",
"uxd",
"react",
"design",
"mcp"
]
},
{
"name": "git",
"source": "./plugins/git",
"description": "Git Plugin",
"version": "0.0.7",
"category": "tooling",
"keywords": [
"git",
"workflow",
"automation"
]
},
{
"name": "github",
"source": "./plugins/github",
"description": "GitHub utilities for image uploads, asset management, and PR automation",
"version": "0.3.0",
"category": "tooling",
"keywords": [
"github",
"screenshots",
"images",
"uploads"
]
},
{
"name": "hello-world",
"source": "./plugins/hello-world",
"description": "HellThe plugins it lists here
This marketplace lists 30 plugins kept in the same repository. Each has its own page, its own measurements and its own install command.
- Plugin golang 8 inside A not measured
- Plugin metrics A not measured
- Plugin node-bug 1 inside A not measured
- Plugin node-team 5 inside A not measured
- Plugin ci-extras 4 inside A not measured
- Plugin code-review 7 inside A not measured
- Plugin node-cve 3 inside A not measured
- Plugin node-onboarding 2 inside A not measured
- Plugin node-rpm 1 inside A not measured
- Plugin operator-dashboard 2 inside A not measured
- Plugin agentic-docs 7 inside A not measured
- Plugin ai-sbom 1 inside A not measured
- Plugin bigquery 1 inside A not measured
- Plugin bigquery-ci-data 5 inside A not measured
- Plugin bigquery-cost-analysis 2 inside A not measured
- Plugin ci 59 inside A not measured
- Plugin compliance 10 inside A not measured
- Plugin console 2 inside A not measured
- Plugin etcd 2 inside A not measured
- Plugin github 3 inside A not measured
- Plugin hcp 8 inside A not measured
- Plugin marketplace-ops 2 inside A not measured
- Plugin node 1 inside A not measured
- Plugin node-tuning 3 inside A not measured
- Plugin agendas 1 inside A not measured
- Plugin git 12 inside A not measured
- Plugin jira 30 inside A not measured
- Plugin must-gather 4 inside A not measured
- Plugin nid-team 4 inside A not measured
- Plugin hello-world 1 inside A not measured
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 6700ce69323f
- yesterday Changed 44e41f038067
- 5d ago Changed f5529719497b
- 6d ago Changed 426b0b52bc21
- 7d ago Changed fdcef31a0243
- 8d ago Changed c0984b47be9c
- 9d ago Changed 6fa95ea86121
- 15d ago Changed 1c5ceab41ec5
- 16d ago Changed · +14 lines 5bc57d5212c8
- 19d ago First seen · 578 lines scan A 512fbc077f7b
ai-helpers marketplace is a plugin published in the GitHub repository openshift-eng/ai-helpers (121 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 2026-08-30.
Other plugins, from other repositories
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.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.