---
name: Agentic Engineering
slug: agentic-engineering
category: AI Engineering
description: Agentic Engineering guides agents through eval-first execution, task decomposition, and cost-aware model routing. Use it when planning or executing engineering work that agents will carry out end to end.
github: "https://github.com/affaan-m/ECC/tree/main/skills/agentic-engineering"
language: JavaScript
stars: 239790
forks: 36398
install: "npx degit https://github.com/affaan-m/ECC/tree/main/skills/agentic-engineering ~/.claude/skills/agentic-engineering"
installs_to: ~/.claude/skills/agentic-engineering
source_path: skills/agentic-engineering/SKILL.md
collection_size: 25
category_size: 2451
collection_url: "https://dirskills.com/collections/affaan-m/ECC"
added: 2026-08-13T07:35:26.126Z
last_synced: 2026-08-13T07:35:26.126Z
canonical_url: "https://dirskills.com/skills/agentic-engineering"
---

# Agentic Engineering

Agentic Engineering guides agents through eval-first execution, task decomposition, and cost-aware model routing. Use it when planning or executing engineering work that agents will carry out end to end.

**Install:**

```bash
npx degit https://github.com/affaan-m/ECC/tree/main/skills/agentic-engineering ~/.claude/skills/agentic-engineering
```

## README

# Agentic Engineering

Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.

## Operating Principles

1. Define completion criteria before execution.
2. Decompose work into agent-sized units.
3. Route model tiers by task complexity.
4. Measure with evals and regression checks.

## Eval-First Loop

1. Define capability eval and regression eval.
2. Run baseline and capture failure signatures.
3. Execute implementation.
4. Re-run evals and compare deltas.

## Task Decomposition

Apply the 15-minute unit rule:
- each unit should be independently verifiable
- each unit should have a single dominant risk
- each unit should expose a clear done condition

## Model Routing

- Haiku: classification, boilerplate transforms, narrow edits
- Sonnet: implementation and refactors
- Opus: architecture, root-cause analysis, multi-file invariants

## Session Strategy

- Continue session for closely-coupled units.
- Start fresh session after major phase transitions.
- Compact after milestone completion, not during active debugging.

## Review Focus for AI-Generated Code

Prioritize:
- invariants and edge cases
- error boundaries
- security and auth assumptions
- hidden coupling and rollout risk

Do not waste review cycles on style-only disagreements when automated format/lint already enforce style.

## Cost Discipline

Track per task:
- model
- token estimate
- retries
- wall-clock time
- success/failure

Escalate model tier only when lower tier fails with a clear reasoning gap.