Instructions file GitHub Copilot
Instructions for DUBSOpenHub/dark-factory, covering copilot instructions — dark factory, file map, non-negotiables, prohibited actions and pr requirements.
23 28d ago A 680 tokens
original MIT
Instructions file CodexOpenCode
Instructions for DUBSOpenHub/dark-factory, covering agents.md — working guide for ai agents, architecture, file ownership map, before you change anything and agent prompt rules.
23 28d ago A 1,617 tokens
original MIT
dark-factory
03Skill Claude CodeCodex
🏭 Dark Factory — agentic build system with sealed-envelope testing. Orchestrates 8 specialist agents through a gated pipeline with cross-family adversarial validation. Say "dark factory" to build something, "dark factory express" for quick tasks, "dark factory tournament" to race model families against one sealed…
23 28d ago D 68 tokens
original MIT
arch-critic
04Agent
Independent architecture reviewer that finds design defects before any code exists. Must be a different model family than the Architect.
23 28d ago A 26 tokens
original MIT
architect
05Agent
Pragmatic architect that turns a PRD into a concrete technical design favoring simplicity.
23 28d ago A 20 tokens
original MIT
lead-eng
06Agent
Senior engineer that implements features per the architecture and writes open tests.
23 28d ago A 16 tokens
original MIT
Agent
Post-ship analyst that evaluates delivered code against PRD success criteria and KPIs. Runs after merge to verify the build actually achieved its goals.
23 28d ago A 34 tokens
original MIT
product-mgr
08Agent
Crisp PM that turns a raw goal into a tight PRD with Given/When/Then acceptance criteria.
23 28d ago A 27 tokens
original MIT
qa-sealed
09Agent
Paranoid QA that writes behavioral tests from the spec alone — never sees implementation code.
23 28d ago A 21 tokens
original MIT
qa-validator
10Agent
Methodical analyst that runs both test suites and produces the Shadow Score with failure details, in Shadow Score Spec v2.0 conformant markdown + JSON.
23 28d ago A 34 tokens
original MIT
red-team
11Agent
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
23 28d ago A 29 tokens
original MIT
Skill Claude CodeCodex
../../../skills/havoc-hackathon/SKILL.md.
5 1mo ago A 0 tokens
original MIT
Instructions file CodexOpenCode
Instructions for DUBSOpenHub/havoc-hackathon, covering agents, available agents, havoc-hackathon (skill), havoc-hackathon (agent) and grid-medic.
5 1mo ago A 677 tokens
original MIT
grid-medic
14Agent
Self-healing meta-agent that monitors, repairs, and continuously improves all Camp Air agents. Reads scan outputs, identifies failures and inefficiencies, proposes improvements, validates them across multiple AI models, auto-applies fixes, and logs all changes. Run after any agent scan to trigger the improvement…
5 1mo ago A 89 tokens
original MIT
Agent
../skills/havoc-hackathon/SKILL.md.
5 1mo ago A 0 tokens
original MIT
Instructions file GitHub Copilot
Instructions for DUBSOpenHub/swarm-command, covering copilot instructions — swarm command, file map, non-negotiables, prohibited actions and pr requirements.
5 25d ago A 650 tokens
original MIT
Skill Claude CodeCodex
🐝 Swarm Command — multi-model consensus swarm orchestrator. Launches 50-250+ AI agents across 15 models with hierarchical fan-out, cross-family review, Shadow Score Spec L2 conformance, and quality-gated synthesis. Say "swarm command", "swarmcommand", or "swarm250" to start.
5 25d ago A 73 tokens
original MIT
Instructions file CodexOpenCode
Instructions for DUBSOpenHub/swarm-command, covering agents, available agents, swarm-command (skill), swarm-command (agent) and file ownership.
5 25d ago A 1,455 tokens
original MIT
Agent
🐝 Swarm Command — multi-model consensus swarm orchestrator. Launches 50-250+ AI agents across 15 models with hierarchical fan-out, cross-family review, shadow scoring, and quality-gated synthesis. Say "swarm command", "swarmcommand", or "swarm250" to start.
5 25d ago A 68 tokens
original MIT
Instructions file CodexOpenCode
Instructions for DUBSOpenHub/groundhog-day, covering agents.md: working guide for ai agents, architecture, file ownership map, key design decisions and 1. no external dependencies beyond standard tools.
5 2mo ago A 900 tokens
original MIT