adonai-labs/agent-runway

Operational discipline layer for AI-assisted software delivery: spec/ticket workflows, quality gates, and persistent engineering memory across Cursor, Claude Code, and VS Code.

2Stars on the repository
85Mods indexed here, across every type
17d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

architect

01

adonai-labs/agent-runway

Skill Claude CodeCodex

Senior software architect and principal engineer reasoning — stack-agnostic. Evaluates design proposals, trade-offs, boundaries, complexity, and system evolution. Use when the user says "/architect", "design this", "evaluate this approach", "is this too complex", "architecture review", "trade-off analysis", "should I…

not rated 2 17d ago A 103 tokens original MIT

autonomous-lead

02

adonai-labs/agent-runway

Skill Claude CodeCodex

Autonomous implementation workflow for low-supervision execution with mandatory decision logging. Executes end-to-end without interactive approval gates, but persists auditable run logs and architecture decisions in project artifacts. Use when the developer asks for autonomous mode, low supervision, or unattended…

not rated 2 17d ago A 57 tokens original MIT

checkpoint

03

adonai-labs/agent-runway

Skill Claude CodeCodex

Capture the current work state so a developer, another agent, or a future session can resume without losing context. Use when the developer says "checkpoint", "save state", "checkpoint this", "handoff", "pause here", or "resume later".

not rated 2 17d ago A 53 tokens original MIT

code-review

04

adonai-labs/agent-runway

Skill Claude CodeCodex

Systematic, evidence-based code review — runs mandatory searches before any manual analysis, then produces a structured report with severity-classified findings. Stack-agnostic core with stack-specific searches and commands injected at install time. Use when the user says "/review", "code review", "review this", "PR…

not rated 2 17d ago A 92 tokens original MIT

contrarian

05

adonai-labs/agent-runway

Skill Claude CodeCodex

Adversarial reviewer for high-impact decisions. Challenges the chosen approach from a clean, skeptical perspective — counter-argument, viable alternative, failure signals, and a Go/Go with conditions/Stop verdict.

not rated 2 17d ago A 44 tokens original MIT

council

06

adonai-labs/agent-runway

Skill Claude CodeCodex

Preview skill for council review of an idea, hypothesis, or implementation direction from multiple perspectives before turning it into a spec, ticket, ADR, or code change. Use when the developer says "council", "idea review", "validate this idea", "review this hypothesis", "should we build this", "implementation…

not rated 2 17d ago A 88 tokens original MIT

express

07

adonai-labs/agent-runway

Skill Claude CodeCodex

Minimal-friction implementation path for well-scoped tasks. Assumes the developer has full context, knows the codebase, and does not need planning ceremony. Use when the developer says "/express", wants to move fast on a well-understood single-layer change, or explicitly opts out of the full workflow.

not rated 2 17d ago A 63 tokens original MIT

iac

08

adonai-labs/agent-runway

Skill Claude CodeCodex

Infrastructure as Code for .NET on Azure - defines, reviews, and troubleshoots Bicep and Terraform for .NET applications. Use when the user says "/iac", "infrastructure", "Bicep", "Terraform", "ARM template", "provision resources", "Azure resources", "deploy infra", "cloud setup", "new environment", or wants to…

not rated 2 17d ago A 90 tokens original MIT

lead

09

adonai-labs/agent-runway

Skill Claude CodeCodex needs its repo

Senior implementation lead — orchestrates the full feature lifecycle from problem exploration to commit. Enforces gated approval before writing code, incremental quality checks during implementation, and handoff to code-review for final validation. Stack-agnostic by default; loads stack-specific references when a…

not rated 2 17d ago A 100 tokens original MIT

learning

10

adonai-labs/agent-runway

Skill Claude CodeCodex

Capture a durable project lesson in Agent Runway memory. Use when the developer says "learning", "remember this", "save this lesson", "add to memory", or when a completed task reveals a recurring decision, failure, convention, or guardrail that should influence future work.

not rated 2 17d ago A 58 tokens original MIT

po-eval

11

adonai-labs/agent-runway

Skill Claude CodeCodex

Evaluates product quality of specs and tickets before implementation. Focuses on business value, clarity, scope, success metrics, risks, dependencies, and readiness from a Product Owner perspective. Use when the user says "/po-eval", "evaluate this spec", "evaluate this ticket from PO view", or "is this product-ready".

not rated 2 17d ago A 70 tokens original MIT

refactor

12

adonai-labs/agent-runway

Skill Claude CodeCodex

Guides structured refactoring to improve readability, maintainability, and SOLID/Clean Architecture alignment — without changing observable behaviour. Deepest examples are in .NET/C#, but the workflow applies to any stack. Use when the user says "/refactor", "clean up", "improve this", "simplify", "restructure"…

not rated 2 17d ago A 95 tokens original MIT

safety-check

13

adonai-labs/agent-runway

Skill Claude CodeCodex

Lightweight risk check before continuing with a fast change. Use when the developer says "safety check", "risk check", "before I continue", "is this safe", or when a Lite workflow touches contracts, data, auth, secrets, deployment, or many files.

not rated 2 17d ago A 59 tokens original MIT

spec-creator

14

adonai-labs/agent-runway

Skill Claude CodeCodex

Creates implementation-ready specs from brief descriptions, existing markdown requirements, or prior specs. Adapts the ticket-creator workflow to spec-engineering with structured lifecycle states, execution planning, and quality gates. Use when creating or refining specs under .agent-runway/specs.

not rated 2 17d ago A 58 tokens original MIT

start

15

adonai-labs/agent-runway

Skill Claude CodeCodex

Entry point for any development task. Understands what the developer wants to do, classifies the intent and complexity, loads relevant project context, and routes to the right skill. Use when a developer doesn't know where to start, says "/start", "where do I begin", "I need to", "how do I", "I want to build", "I need…

not rated 2 17d ago A 90 tokens original MIT

ticket-creator

16

adonai-labs/agent-runway

Skill Claude CodeCodex

Creates ready-to-dev tickets from brief descriptions, Jira tickets, or markdown files. Combines PO and BA perspectives to generate complete tickets with context, scope, acceptance criteria, dependencies, and QA notes. Use when creating tickets, writing user stories, preparing backlog items, or refining requirements.

not rated 2 17d ago A 61 tokens original MIT

ticket-eval

17

adonai-labs/agent-runway

Skill Claude CodeCodex

Evaluates tickets and user stories for development readiness. Classifies ticket type, checks completeness against defined criteria, detects implementation antipatterns, and produces a structured report with a clear READY TO DEV verdict. Use when the user says "ticket eval", "validate ticket", "is this ready", "check…

not rated 2 17d ago A 82 tokens original MIT

dotnet-core

18

adonai-labs/agent-runway

Skill Claude CodeCodex

.NET and C# implementation guidance — stack-specific. Covers application patterns, infrastructure, observability, testing, security, and API design for .NET 8/9 applications. Use when the user asks how to implement something in .NET, whether C# code is idiomatic, MediatR/EF Core patterns, .NET testing, observability…

not rated 2 17d ago A 120 tokens original MIT

go-core

19

adonai-labs/agent-runway

Skill Claude CodeCodex

Go implementation guidance — stack-specific. Covers project structure, idiomatic patterns, testing, security, and observability for Go backend services and CLIs. Use when the user asks about Go-specific structure, error handling, concurrency, testing strategy, or production reliability. Invoke via @go-core after…

not rated 2 17d ago A 76 tokens original MIT

node-core

20

adonai-labs/agent-runway

Skill Claude CodeCodex

Node.js implementation guidance — stack-specific. Covers architecture, async patterns, process lifecycle, testing, security, and observability for Node.js backend services, APIs, workers, and CLIs. Use when the user asks about Node.js-specific patterns, process management, stream handling, or production reliability.…

not rated 2 17d ago A 93 tokens original MIT

python-core

21

adonai-labs/agent-runway

Skill Claude CodeCodex

Python implementation guidance — stack-specific. Covers project structure, clean architecture, testing with pytest, security, and observability for Python backend services and APIs. Use when the user asks about Python-specific patterns, structuring a service, testing strategy, or production reliability. Invoke via…

not rated 2 17d ago A 76 tokens original MIT

react-core

22

adonai-labs/agent-runway

Skill Claude CodeCodex

React implementation guidance — stack-specific. Covers project structure, component patterns, state management, testing with React Testing Library, security, accessibility, and performance for React 18+ applications. Use when the user asks about React-specific structure, hooks, state decisions, testing strategy, or…

not rated 2 17d ago A 89 tokens original MIT

rust-core

23

adonai-labs/agent-runway

Skill Claude CodeCodex

Rust implementation guidance — stack-specific. Covers project structure, idiomatic patterns, ownership, error handling, testing, security, and observability for Rust backend services and CLIs. Use when the user asks about Rust-specific patterns, ownership, async with Tokio, testing strategy, or production reliability.…

not rated 2 17d ago A 82 tokens original MIT

typescript-core

24

adonai-labs/agent-runway

Skill Claude CodeCodex

TypeScript implementation guidance — stack-specific. Covers architecture, application patterns, testing, security, observability, and API design for TypeScript applications. Use when the user asks how to structure TypeScript code, type-safe patterns, testing strategies, or security practices. Invoke via skill…

not rated 2 17d ago A 87 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: