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/curie-eng/curieWrote 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/curie-eng/curie/dark-factory)<a href="https://agentmods.dev/plugins/curie-eng/curie/dark-factory"><img src="https://agentmods.dev/badge/plugins/curie-eng/curie/dark-factory/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/curie-eng/curie/dark-factory"><img src="https://agentmods.dev/badge/plugins/curie-eng/curie/dark-factory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dark-factory 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 12d 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": "dark-factory",
"version": "0.1.0",
"description": "Curie's default dark factory agent: one labelled GitHub issue in, one reviewed pull request or one stated reason out. One agent reads the issue through the platform's get_issue tool, pins acceptance criteria, plans, gets the plan reviewed by an Opus plan-reviewer subagent, writes a failing test where feasible, implements and runs the repository's own checks, gets the diff reviewed by an Opus diff-reviewer subagent (each loop capped at 3 rounds, enforced by a hook), and publishes through Curie's built-in approval-gated publication tool within the 10800 second (3 hour) execution bound.",
"author": { "name": "CurieTech" },
"license": "Apache-2.0",
"keywords": ["factory", "coding", "github", "issues", "pull-request"],
"starterPrompts": [
"https://github.com/acme-corp/acme-bot/issues/1"
]
}
What it installs
The manifest is a name and a version. 1 skill, 4 hooks travel with it, and installing the plugin installs all of them — 38 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.
- 12d ago Changed · -7 lines ab69ee8a080a
- 18d ago First seen · 19 lines scan A 474a62562f42
dark-factory is a plugin published in the GitHub repository curie-eng/curie (36 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 2026-09-26.
Other plugins, from other repositories
branch-recap
Tells you what your branch actually changed — what was done, why, and what deserves a second look, instead of the diff — then files the fixes into the commits they belong to.
g-forge
Educated, enforced project management for AI development - a PM layer, parallel implementation waves, and a git-hook commit gate that can't be skipped. Make any model ship like a senior team.
dootask
A DooTask plugin toolkit for creating plugins, preparing releases, improving project instructions, and making Conventional Commits. Conventional Commits are a standard format for describing Git changes.
github
Skills for GitHub pull request workflows — creating PRs, addressing review feedback, and resolving threads.
open-source
Collection of skills for open-source R and Python package developers.
agent-army
Deploy a 2-layer parallel agent hierarchy for large, parallelizable work: big refactors, multi-file migrations, codebase-wide audits, and bulk generation. Pick an army size and power level; includes git checkpoints, a pre-deploy gate, phantom-completion checks, and multi-wave follow-up.