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/handarbeit/fabrikWrote 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/handarbeit/fabrik/fabrik-workflows)<a href="https://agentmods.dev/plugins/handarbeit/fabrik/fabrik-workflows"><img src="https://agentmods.dev/badge/plugins/handarbeit/fabrik/fabrik-workflows/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/handarbeit/fabrik/fabrik-workflows"><img src="https://agentmods.dev/badge/plugins/handarbeit/fabrik/fabrik-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fabrik-stages 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 4d 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": "fabrik-stages",
"version": "0.2.0",
"description": "SDLC stage workflow skills for the Fabrik pipeline orchestrator. Provides expertise for each pipeline stage: Specify, Research, Plan, Implement, Review, and Validate.",
"author": {
"name": "handarbeit.io",
"url": "https://handarbeit.io"
},
"homepage": "https://github.com/handarbeit/fabrik",
"repository": "https://github.com/handarbeit/fabrik"
}
What it installs
The manifest is a name and a version. 12 skills travel with it, and installing the plugin installs all of them — 477 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill validate A 36 tokens
- Skill review A 35 tokens
- Skill implement A 38 tokens
- Skill plan A 35 tokens
- Skill review-comment A 43 tokens
- Skill validate-comment A 46 tokens
- Skill implement-comment A 38 tokens
- Skill specify A 41 tokens
- Skill research A 35 tokens
- Skill specify-comment A 37 tokens
- Skill plan-comment A 48 tokens
- Skill research-comment A 45 tokens
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.
- 4d ago Changed ccf9b167ecb7
- 1mo ago First seen · 12 lines scan A 6c0546eee96e
fabrik-stages is a plugin published in the GitHub repository handarbeit/fabrik (24 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
flutter-flame-harness
Idea-to-store harness for Flutter/Flame games: research (AI idea recommendation), plan, design, contract, generator-evaluator build loop, AdMob, build, screenshot, submit, retro.
harness
Portable read-only advisor agents, profile-driven PR/ticket skills, enforcement hooks, and a self-adapting /harness-init that tailors any repo to a documented index pattern.
agent-evaluation
Comprehensive evaluation framework for LLM agent systems. Multi-dimensional rubrics, LLM-as-judge with bias mitigation, pairwise comparison, direct scoring, confidence calibration, and continuous monitoring.
competitive-intelligence
Competitor analysis, market sizing, positioning maps, win/loss pattern synthesis, and battlecard creation for product and GTM decisions.
context-compression
Production strategies for compressing LLM context windows. Anchored iterative summarization, opaque compression, tokens-per-task optimization, and probe-based evaluation.
context-degradation
Patterns for recognizing and mitigating context failures in LLM agents. Covers lost-in-middle, context poisoning, distraction, confusion, clash, and model-agnostic degradation measurement.