loki-mode

Agent SkillsFreeOpen Source

Multi-agent autonomous SDLC skill: from PRD/brief to deployed app with quality gates.

🛡️ AgentReady threat assessment

MAESTRO 7-layer threat model + OWASP AIVSS risk score for loki-mode, derived from its capabilities.

AIVSS 9.0 · Critical

These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.

Overview

Community skill that runs a multi-agent autonomous software-development framework, orchestrating many agents/swarms to go from a spec (PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief) to a built and deployed app. Uses multiple AI providers and 11 quality gates; heavy orchestration and code-execution surface.

Key features and capabilities

Multi-agent SDLC orchestration
Spec-to-deployed-app pipeline
11 quality gates, 5 providers

Use cases

Autonomous app building
End-to-end delivery from a brief