Back to Skills

Loki Mode

Name: Loki Mode
Author: asklokesh

from asklokesh

Autonomous spec-driven build system that transforms specifications into verified products with a built-in trust layer.

triggers:Loki Modeautonomous buildspec-driven developmentRARV-C closureautonomous software engineering

Loki Mode is a multi-agent autonomous SDLC framework designed to take a specification (PRD, GitHub issue, OpenAPI doc) and produce a deployed, verified product with minimal human intervention.

Core Features:

Trust Layer: Implements the RARV-C closure loop, 8 quality gates, and a completion council to ensure work is verified, not just claimed.
Evidence Receipts: Generates deterministic proofs of completion, separating facts (git diffs, test exit codes) from AI assessments.
Provider Agnostic: Supports multiple AI providers including Claude, Codex, Cline, and Aider.
Phase-Based Workflow: Orchestrates the entire lifecycle from Bootstrap and Discovery through Architecture, Development, QA, and Deployment.
Autonomous Decision Making: Operates under strict rules to decide and act without constant user confirmation, maintaining high momentum.

Not yet audited

This skill has not been reviewed by our automated audit pipeline yet.

Information

Repository: asklokesh

Related Skills

Maestro Orchestrate

Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.

Run Execute

Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

Bash Pro

Defensive, production-grade Bash scripting patterns and CI/CD best practices: strict mode, safe argument parsing, testing with Bats, and tooling (ShellCheck/shf

Terragrunt Infrastructure

Best-practice patterns and operational guidance for Terragrunt/OpenTofu infrastructure: catalog/live/module layout, state backend setup, and deployment workflow

Build Unplanned Feature

Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo

AI Pair Collaboration

Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate

Box0 (b0)

Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.

Bats Testing Patterns

Practical patterns and examples for writing maintainable unit tests for shell scripts using Bats (Bash Automated Testing System).

MCP App Store