Agent skill · software engineering · affaan-m
agentic-engineering
Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when AI agents perform most implementation work and humans enforce quality and risk controls.
Why this skill is useful
Provides a structured framework for managing AI-driven development workflows, including task decomposition and model tier selection that the AI wouldn't reliably generate on its own.
What it needs
About 2k tokens when loaded. Last updated 2026-08-06. 238,342 stars on the source repository.
What this skill does
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. Example workflow: 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 Good decomposition: Bad decomposition: Model Routing Choose model tier based on task complexity: Haiku: Classification, boilerplate transforms, narrow edits Example: Rename variable, add type annotation, format code Sonnet: Implementation and refactors Example: Implement feature, refactor module, write tests Opus: Architecture, root-cause analysis, multi-file invariants Example: Design system, debug complex issue, review architecture Cost discipline: Escalate model tier only when lower tier fails with a clear reasoning gap. Session Strategy Continue session for closely-coupled units Example: Implementing related functions in same module Start fresh session after major phase transitions Example: Moving from implementation to testing Compact after milestone completion, not during active debugging Example: After feature complete, before starting next feature 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. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills affaan-m/agentic-engineering