# Agentic Engineering

> Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing.

- Skill: `thedixitjain/agentic-engineering-4` (Agent Skill)
- Install (CLI): `npx skillmds add thedixitjain/agentic-engineering-4`
- Raw SKILL.md: https://api.skillmd.com/api/skills/thedixitjain/agentic-engineering-4/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: thedixitjain (https://skillmd.com/u/thedixitjain)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/thedixitjain/agentic-engineering-4

---

# 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.

---

**Source:** [`affaan-m/ECC`](https://github.com/affaan-m/ECC) → `skills/agentic-engineering/SKILL.md`

**Also appears in:** `hashgraph-online/awesome-codex-plugins/plugins/Colin4k1024/tsp/skills/agentic-engineering/SKILL.md`