SkillsSKILLS
Productivity

agentic-engineering▌

affaan-m/everything-claude-code · updated Apr 8, 2026

$npx skills add https://github.com/affaan-m/everything-claude-code --skill agentic-engineering
summary

AI-driven engineering workflows with eval-first execution, task decomposition, and cost-aware model routing.

  • ›Defines an eval-first loop: establish baseline evals before implementation, then re-run post-execution to measure deltas and catch regressions
  • ›Decomposes work into 15-minute units with single dominant risks, independent verifiability, and clear done conditions
  • ›Routes tasks by complexity: Haiku for classification and boilerplate, Sonnet for implementation, Opus for architecture
skill.md

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.