agentic-engineering

Coordinate agent-based engineering workflows with human quality controls.

1|Updated Feb 13, 2026

Search Tags:#automation #decomposition #engineering #agentic #model-routing #eval-first #cost-discipline

Ready to run

npx skills add https://github.com/ROLLED740/vibe-clone-pro --skill agentic-engineering-rolled740

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agentic-engineering
Source: https://github.com/ROLLED740/vibe-clone-pro/tree/main/.agent/skills/agentic-engineering
Command: npx skills add https://github.com/ROLLED740/vibe-clone-pro --skill agentic-engineering-rolled740

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrates agentic engineering workflows to allow AI agents to perform most implementation work while humans enforce quality and risk controls, reducing handoff bottlenecks and accelerating delivery.

Core Features & Use Cases

Eval-first loop with capability eval and regression eval to detect failures early
Decompose work into agent-sized units that are independently verifiable
Route models by task complexity (Haiku: classification/boilerplate transforms, Sonnet: implementation/refactors, Opus: architecture/root-cause analysis)
Enforce session strategy and compact reviews after milestones
Emphasize invariants, error handling, security assumptions, and risk in AI-generated code
Track cost metrics per task: model, token estimates, retries, wall-clock time, success/failure

Quick Start

Provide a task outline to an agentic engineer and begin the eval-first workflow to decompose, implement, and verify with regression checks.

Frequently Asked Questions about agentic-engineering

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

FAQPage Schema

How do I automate engineering workflows using AI agents?▼

To automate engineering workflows using AI agents, provide a task outline to an agentic engineer to decompose work into verifiable units, route models by complexity, and execute iterative regression checks.

What is an eval-first execution loop for agentic engineering?▼

An eval-first execution loop defines capability and regression evaluations to run baselines before implementation, capturing failure signatures early and re-running evaluations after code changes to detect regressions.

How does model routing work in automated engineering tasks?▼

Model routing assigns tasks by complexity: Haiku handles classification and boilerplate transforms, Sonnet executes implementations and refactors, while Opus manages architecture design and root-cause analysis to optimize cost.

How do I track AI agent cost metrics and token usage per task?▼

Track AI agent cost metrics per task by monitoring the specific model utilized, token estimates, execution retries, wall-clock time, and the final success or failure status across different model tiers.

Can I enforce security assumptions and error handling in AI-generated code?▼

You can enforce security assumptions and error handling in AI-generated code by emphasizing invariants during the session strategy and compacting reviews after milestones to maintain human quality and risk controls.