rlm-workflow

Orchestrate phase-gated RLM runs with SHA-256 LockHash verification and artifact locking.

67|2|Updated Feb 7, 2026
One-click install
npx skills add https://github.com/doubleuuser/rlm-workflow --skill rlm-workflow
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rlm-workflow
Source: https://github.com/doubleuuser/rlm-workflow/tree/main
Command: npx skills add https://github.com/doubleuuser/rlm-workflow --skill rlm-workflow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

RLM-workflow enforces a disciplined, reproducible repository-driven development process so that requirements, plans, tests, and QA live in durable files rather than transient chat context. It prevents context rot, accidental main-branch pollution, and undocumented shortcuts by requiring sequential phase gates, immutable locks, and explicit user sign-off for manual QA.

Core Features & Use Cases

  • Orchestrates end-to-end RLM phases (worktree isolation, AS-IS analysis, optional root-cause debugging, TO-BE planning, TDD implementation, review, parallel testing, manual QA, and global updates).
  • Enforces TDD discipline, Coverage and Approval gates, LockHash (SHA-256) verification, addenda policy, and TODO completion rules to produce auditable run artifacts.
  • Supports parallel subagent execution with automatic fallback to sequential mode, plus utilities to initialize runs, lint artifacts, verify locks, and report run status.
  • Use case example: implement a feature or fix a bug as a resumable, single-command RLM run where each phase is documented, validated, and locked for auditability.

Quick Start

Implement requirement 2026-02-24-add-oauth to execute the full RLM run for that requirement.

Frequently Asked Questions about rlm-workflow

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce a TDD-first workflow with isolated git worktrees?▼

You can enforce a TDD-first workflow with isolated git worktrees by orchestrating phase-gated execution that requires worktree isolation, AS-IS analysis, and test-driven implementation before any review or QA phase proceeds.

What is the best way to prevent context rot in repository-driven development?▼

Preventing context rot in repository-driven development requires storing requirements, plans, tests, and QA in durable files under .codex/rlm run folders rather than transient chat context, ensuring sequential phase gates and immutable locks.

How does SHA-256 LockHash verification work for artifact locking?▼

SHA-256 LockHash verification works by generating a hash for run artifacts to enforce addenda-based immutability, ensuring that once a phase gate passes, its evidence collection remains auditable and tamper-proof.

Can I use parallel subagent execution for TDD implementation and testing?▼

Yes, you can use parallel subagent execution for TDD implementation and parallel testing, which includes automatic fallback to sequential mode if subagent parallelization encounters constraints during the run.

Does phase-gated workflow execution require manual QA sign-off?▼

Yes, phase-gated workflow execution requires explicit user sign-off for manual QA gates to prevent undocumented shortcuts and ensure standardized evidence collection before global updates are applied.

Why should I use systematic root-cause debugging before TO-BE planning?▼

Using systematic root-cause debugging before TO-BE planning ensures that the underlying issue is identified during the AS-IS analysis phase, preventing accidental main-branch pollution and producing auditable run artifacts.