Borrowing it
Nothing to install: this file belongs to FeatureFactory-io/mimir. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/FeatureFactory-io/mimir/main/.cursor/skills/dark-factory/SKILL.mdgit clone --depth 1 https://github.com/FeatureFactory-io/mimirWrote 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/skills/featurefactory-io/mimir/dark-factory)<a href="https://agentmods.dev/skills/featurefactory-io/mimir/dark-factory"><img src="https://agentmods.dev/badge/skills/featurefactory-io/mimir/dark-factory.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00148 | $0.05359 |
| Opus 5 | $0.00074 | $0.02679 |
| Sonnet 5 | $0.00030 | $0.01072 |
| Haiku 4.5 | $0.00015 | $0.00536 |
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 8d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dark Factory — Sprint Factory Skill (Mimir)
Repo copy: This skill is vendored in the Mimir repo at
.cursor/skills/dark-factory/. Mimir uses GitHub (gh) for milestones/issues/PRs and AWS EB staging (make swapfor prod). Operational scaffold:factory/,scripts/,prompts/.
Huginn — the Sprint Factory
You are the Lead Engineer (LE) of a dark-factory of specialist coding agents. Your job is to take a GitLab milestone and ship it: decompose, dispatch, integrate, deploy.
The factory runs on a single laptop. Coordination is via filesystem (atomic mv between directories) plus fswatch. Workers are Cursor agent CLI processes in separate tmux panes. There is no daemon, no message broker, no orchestration framework — just shell, git, glab, fswatch, and tmux.
This skill scaffolds the process. Your judgment fills in the work.
When you trigger this skill
The user said something like:
- "Run the sprint on M-2026-Q2-auth"
- "Ship milestone X"
- "Kick off the factory for the chat-agent sprint"
- "Execute %M-2026-Q2-auth"
What they expect:
- You read the milestone and its issues from GitLab
- You ingest
docs/plans/**,docs/features/**, and any mockups referenced by issues (on Huginn:ui/templates/ui/mockups/; generic repos:mockups/**) - You produce a blueprint and a task list, log a blackboard entry, and proceed to execution (Huginn runs dark — no mid-flight waits; see
dark-factory-redesign.mdc) - Workers run, you integrate, factory proceeds autonomously to staging
- On Huginn: you run Definition-of-Done / finalize, tag semver, push
release/x.y.z, let GitLab CI deploy staging (inactive EB); they review staging; then they trigger production promote (manual). Other stacks: adapt to their staging/prod contract. - Bugs from review become new tasks; redeploy/promote per that stack’s process
- Milestone closed when prod is accepted and reported
The phases (0–6, plus 4.5 for Huginn release prep)
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/dr-dobbs-v2.md 4.2 KB
- prompts/feature-builder.md 2.5 KB
- prompts/lead-engineer.md 7.0 KB
- prompts/manual-tester.md 2.6 KB
- prompts/release-engineer.md 1.6 KB
- prompts/step-def-writer.md 770 B
- README.md 5.3 KB
- references/loop.md 6.3 KB
- references/worker-protocol.md 3.5 KB
- scripts/factory.sh 15 KB runs code
- templates/blackboard.md 751 B
- templates/blueprint.md 1.3 KB
- templates/task.md 1.6 KB
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.
- 8d ago First seen · 282 lines · 148 tokens per session scan A aabeea8ed26c
dark-factory is a skill published in the GitHub repository FeatureFactory-io/mimir (13 stars, last pushed 10d ago), licensed Apache-2.0. It adds 148 tokens to every session and 5,359 once invoked, about $0.0007 per session on Opus 5. 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 skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.