nicelight/DevRails-26

nicelight/DevRails-26

Command Claude Code

Add the cheapest sufficient regression coverage inside one existing in-progress indexed task.

nicelight/DevRails-26

Command Claude Code

Bounded C4 and architecture review of one feature's task-planning surface for a fresh Reviewer.

nicelight/DevRails-26

Command Claude Code

Run the complete unattended DevRails workflow from authoritative product input to a terminal sequential JSON task queue.

nicelight/DevRails-26

Command Claude Code

Sequentially execute an already reviewed and strict-ready indexed product JSON task queue to a terminal state.

nicelight/DevRails-26

Command Claude Code

Adaptively clarify and maintain the Project Constitution governing layer.

nicelight/DevRails-26

Command Claude Code

Build a compact Memory Bank/codebase Context Read Manifest for another agent from a delegated Explorer session; use for broad discovery when direct reads are not already cheaper.

nicelight/DevRails-26

Command Claude Code

Use first for creative work—technical or everyday—when a brief is incomplete or intent is implicit and success depends on taste, voice, feeling, or human experience. Also trigger when literal compliance may lose the point. Do not wait for explicit creative wording. Skip factual lookup, mechanical or exact tasks, and…

nicelight/DevRails-26

Command Claude Code

Diagnose one task failure read-only and route evidence-backed recurrence prevention.

nicelight/DevRails-26

Command Claude Code

Adaptively resolve unknowns and contradictions before planning or coding.

nicelight/DevRails-26

Command Claude Code

Execute one indexed JSON task within its semantic and hard runtime boundaries, then produce tier-routed evidence and handoff.

nicelight/DevRails-26

Command Claude Code

Bounded semantic triage and repair routing for one feature.

nicelight/DevRails-26

Command Claude Code

Plan or reconcile one product feature into canonical SDD coverage, an implementation plan, and complete JSON task cards.

nicelight/DevRails-26

Command Claude Code

A command that loads a project's Memory Bank, a set of documents containing its product details, requirements, design, and working rules, into the agent's context.

nicelight/DevRails-26

Command Claude Code

A project-first search command for finding relevant coding-agent skills, first among skills already installed in the project and then in a marketplace.

nicelight/DevRails-26

Command Claude Code

Convert an accepted Foundation Dev Path decision into the minimum FT-000 JSON queue, or prove an existing brownfield baseline.

nicelight/DevRails-26

Command Claude Code

Apply the deployed Architect proposal preflight to architecture and specification design, findings, and corrections in the current role without changing workflow authority.

nicelight/DevRails-26

Command Claude Code

A command that maps an existing repository into Memory Bank documentation: baseline files that describe how the codebase currently works. It is intended for a brownfield project, meaning an existing codebase rather than a new one.

nicelight/DevRails-26

Command Claude Code needs its repo

Deterministic Memory Bank readiness gate over mb-lint for autonomous/autopilot execution.

nicelight/DevRails-26

Command Claude Code

A command for regularly maintaining a Memory Bank, a set of project notes and specifications used to preserve context. It scans and classifies issues involving stale references, conflicting rules, links, and unfinished notes.

nicelight/DevRails-26

Command Claude Code

Route Memory Bank bootstrap or coherent framework sync through an available external DevRails checkout.

nicelight/DevRails-26

Command Claude Code

Thin adapter that reconciles already-decided task and Memory Bank state at a durable boundary.

nicelight/DevRails-26

Command Claude Code

Run the current autonomous and product-scheduler contracts with phased Judge supervision.

nicelight/DevRails-26

Command Claude Code

Decompose a clarified PRD into Memory Bank product, requirements, epics, and features.

nicelight/DevRails-26

Command Claude Code

Independent adversarial semantic verification for T3 tasks and T2 feature completion.