Agent skill

Dark Factory

by av in av/mi

Autonomous software production with continuous runtime verification.

No licenceAuto-check passedTesting & QA

Install Dark Factory

skills CLI
$ npx skills add av/mi --skill dark-factory -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install av/mi dark-factory --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/av/mi.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/dark-factory .claude/skills/dark-factory && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dark-factory
GitHub stars
102
Token cost
~6.8k tokens
SKILL.md length
2,793 words
Files
5
Skills in repo
21
Repo updated
First seen
Licence
None found

At a glance

Autonomous software production with continuous runtime verification.

  • Works in 6 steps: Intake (User Gate) → Bootstrap & Slicing (Autonomous) → Skeleton (Hard Gate) → …
  • The user says dark factory
  • SKILL.md covers Core Constraint, Core Principles, Compact Workflow and The Slice Model, plus 5 more sections
  • Calls git and gh

What it does

Dark Factory is an agent skill from av/mi. Autonomous software production with continuous runtime verification. Takes a raw idea and produces a fully working product by building depth-first in verified slices. Each slice adds one capability to working software, verified by actually running it before the next begins. Absorbs the best of forge, discipline, timeboxed-iterating, bugbash, and agent-integration-testing into one end-to-end workflow. Use when the user says "dark factory", "build this", "forge this", "make this into a product", or any variant of…

Its SKILL.md is about 6.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `subroutines/bugbash.md`, `subroutines/facts-refine.md` and `subroutines/integration-testing.md`).

It sits in Testing & QA, covering Integration testing. The repository describes itself as: self-extending sandboxed agentic harness. a loop, two tools and an llm.

When your agent uses it

  • The user says dark factory
  • Make this into a product
  • Any variant of turn this idea into working software

Example prompts

  • “dark factory”
  • “build this”
  • “forge this”
  • “/dark-factory”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Intake (User Gate)
  2. Bootstrap & Slicing (Autonomous)
  3. Skeleton (Hard Gate)
  4. Slice Loop (The Factory Floor)
  5. Hardening
  6. Ship

What it can do on your machine

Read from SKILL.md and the folder at commit 2bf50c9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dark Factory loads about 6.8k tokens when it runs. Until then it costs about 142 tokens; SKILL.md has 2,793 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~142
When it runs · the whole SKILL.md, loaded when a task matches
~6.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 2,793 words (~6,839 tokens).

“Turn a raw idea into software that actually works — software a human can run and use right now, not software that "should work."”

— opening of SKILL.md by av
name
dark-factory

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files in .agents/skills/dark-factory of av/mi.

  • SKILL.md
  • subroutines/bugbash.md
  • subroutines/facts-refine.md
  • subroutines/integration-testing.md
  • subroutines/static-review.md

Open the folder on GitHubat commit 2bf50c9

Compare with similar skills

Dark Factory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dark Factory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dark Factory this skillav/mi102—~6.8kAutomated safety check: PassNone
Plugin Testingpolyipseity/obsidian-terminal948—~828Automated safety check: PassAGPL-3.0
Create Modulecartography-cncf/cartography4.1k—~2.5kAutomated safety check: PassApache-2.0
Td Integration Testmarcus/td251—~1.2kAutomated safety check: PassMIT
Integration E2E Testingshinpr/claude-code-workflows691—~3.5kAutomated safety check: PassMIT
JS-in-HTML Testingliaohch3/claude-tap3.3k—~924Automated safety check: PassMIT

Similar skills

  • Plugin Testing

    polyipseity/obsidian-terminal

    Skill for testing Obsidian plugin features in this repository.

    948 GitHub stars~828 tokensUpdated 5 days ago
    Testing & QAAuto-check passed
  • Create Module

    cartography-cncf/cartography

    Author a new Cartography intel module end-to-end (entry point, sync GET/TRANSFORM/LOAD/CLEANUP, declarative data model, integration test, schema docs).

    4.1k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check passed
  • Write integration tests for the td-sync admin API using the TestHarness in internal/api/testharnesstest.go.

    251 GitHub stars~1.2k tokensUpdated 8 days ago
    Testing & QAAuto-check passed
  • Integration E2E Testing

    shinpr/claude-code-workflows

    Integration and E2E test design principles, ROI calculation, test skeleton specification, and review criteria.

    691 GitHub stars~3.5k tokensUpdated 7 days ago
    Testing & QAAuto-check passed
  • JS-in-HTML Testing

    liaohch3/claude-tap

    Tests JavaScript embedded in an HTML file in two layers: pytest checks of the logic ported to Python, and Playwright runs in a real browser for the DOM.

    3.3k GitHub stars~924 tokensUpdated 16 days ago
    Testing & QAAuto-check passed
  • Crosvm Testing

    google/crosvm

    Official

    Skill to assist with running tests and managing test VMs in the crosvm repository.

    1.3k GitHub stars~847 tokensUpdated today
    Testing & QAAuto-check passed
  • Writes plain-English integration test specs with verifiable steps and expectations, then runs each one through a subagent that reports pass or fail with logs.

    102 GitHub stars~908 tokensUpdated 12 days ago
    Auto-check passed
  • Anneal

    av/mi

    A skill your agent uses when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other…

    102 GitHub stars~3.8k tokensUpdated 12 days ago
    Auto-check passed
  • Scans a codebase to tag every fact as draft, spec or implemented based on what the code actually shows, adding missing facts and fixing or removing wrong ones.

    102 GitHub stars~2.8k tokensUpdated 12 days ago
    Auto-check passed
  • Implements every @spec fact from a project's fact sheet in code, tags each one @implemented once done, and reports exactly what is left if it cannot finish.

    102 GitHub stars~1.3k tokensUpdated 12 days ago
    Auto-check passed
  • Works with you to turn draft behavioral facts into precise, implementable spec facts, resolving vague labels, gaps and contradictions one at a time through discussion.

    102 GitHub stars~1.5k tokensUpdated 12 days ago
    Auto-check passed
  • Ideate

    av/mi

    Timeboxed ideation on a topic using propose-and-critique subagent pairs.

    102 GitHub stars~2.8k tokensUpdated 12 days ago
    Auto-check passed

Categories

Questions about Dark Factory

What does Dark Factory do?

Autonomous software production with continuous runtime verification. Dark Factory is an agent skill from av/mi. Autonomous software production with continuous runtime verification.

When should I use Dark Factory?

Dark Factory fits situations like: the user says dark factory; make this into a product; any variant of turn this idea into working software.

How do I install Dark Factory in Claude Code?

Run `npx skills add av/mi --skill dark-factory -a claude-code`. Or copy the skill folder (.agents/skills/dark-factory in av/mi) into .claude/skills/dark-factory in your project. Claude Code loads it when a task matches its description.

How do I install Dark Factory in Codex?

Run `npx skills add av/mi --skill dark-factory -a codex`. Or copy the skill folder (.agents/skills/dark-factory in av/mi) into .agents/skills/dark-factory in your project. Codex loads it when a task matches its description.

Can I use Dark Factory in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add av/mi --skill dark-factory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dark-factory, .gemini/skills/dark-factory, .github/skills/dark-factory and .opencode/skills/dark-factory in your project.

What does Dark Factory need to run?

Going by SKILL.md and its folder, Dark Factory needs the command-line tools its instructions call (git and gh).

Does Dark Factory access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Dark Factory safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dark Factory use?

No licence was found for Dark Factory or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Dark Factory use?

About 6.8k tokens (SKILL.md is roughly 27k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dark Factory?

Skills that share tags, products or a category with Dark Factory: Plugin Testing (polyipseity/obsidian-terminal, 948 stars), Create Module (cartography-cncf/cartography, 4.1k stars), Td Integration Test (marcus/td, 251 stars) and Integration E2E Testing (shinpr/claude-code-workflows, 691 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dark Factory?

av (a GitHub user) maintains it in av/mi, which has 102 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 26, 2026.

Source: av/mi on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.