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/dhofheinz/open-pluginsWrote 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/dhofheinz/open-plugins/refinery)<a href="https://agentmods.dev/plugins/dhofheinz/open-plugins/refinery"><img src="https://agentmods.dev/badge/plugins/dhofheinz/open-plugins/refinery/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/dhofheinz/open-plugins/refinery"><img src="https://agentmods.dev/badge/plugins/dhofheinz/open-plugins/refinery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
refinery 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "refinery",
"version": "1.2.0",
"description": "Unified specification refinement plugin. Single entry point for all spec operations: greenfield architecture pipelines (principles → design → stack → spec → plan), feature spec creation, iterative convergence loops, quality reviews, drift detection, finalization, and dispatch-compatible ticket decomposition. Treats specifications as typed nodes in an artifact graph with first-class confidence and evidence.",
"author": {
"name": "Daniel Hofheinz",
"email": "[email protected]",
"url": "https://github.com/dhofheinz"
},
"license": "MIT",
"repository": "https://github.com/dhofheinz/open-plugins",
"homepage": "https://github.com/dhofheinz/open-plugins/tree/main/plugins/refinery",
"keywords": [
"specification",
"requirements",
"refinement",
"architecture",
"EARS",
"Given-When-Then",
"iterative",
"convergence",
"drift-detection",
"tickets",
"dispatch-compatible",
"documentation",
"planning"
],
"userConfig": {
"working_directory": {
"type": "directory",
"title": "Working directory",
"description": "Default working directory for Refinery artifacts (relative to project root). Defaults to docs/refinery/ if unset. Override per-invocation with --output-dir flag.",
"sensitive": false
},
"spec_writer_model": {
"type": "string",
"title": "Spec writer model",
"description": "Model alias used by the spec-writer agent (sonnet, opus, haiku, or full model ID). Defaults to sonnet, which handles structured template-filling (spec/feature-spec/plan/stack) well. The principles and design stages use opus by default (overridable by this setting) because they synthesize structure from a seed idea.",
"sensitive": false
},
"specialist_model": {
"type": "string",
"title": "Specialist agents model",
"description": "Model alias used by the four specialist agents (speWhat it installs
The manifest is a name and a version. 2 skills, 6 agents travel with it, and installing the plugin installs all of them — 616 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.
- 1mo ago First seen · 49 lines scan A a3f33840ba6d
refinery is a plugin published in the GitHub repository dhofheinz/open-plugins (9 stars, last pushed 6mo 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 2026-08-31.
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.