Agentic Engineering
This is a structured approach to letting AI agents do the grunt work while you stay in control of quality and costs. You define evals before writing code, break work into 15-minute chunks that can be verified independently, and route tasks to Haiku for simple edits or Opus for architectural decisions. The eval-first loop is smart: run tests, capture failures, implement, then compare deltas. What's refreshing is the cost discipline section that actually tells you to track tokens and retries per task, and the review guidance that says skip style nitpicks if you already have automated formatting. If you're shipping features with AI agents instead of just using them for autocomplete, this gives you guard rails without turning into process theater.
- skills.sh installs
- 5.4K
- GitHub stars
- 229.1K
- last updated
- Jul 14, 2026
Install
$ npx -y skills add affaan-m/everything-claude-code --skill agentic-engineering --agent claude-codeInstalls into .claude/skills of the current project.
Files
Agentic Engineering
Use this skill for engineering workflows where AI agents perform most implementation work and humans enforce quality and risk controls.
Operating Principles
- Define completion criteria before execution.
- Decompose work into agent-sized units.
- Route model tiers by task complexity.
- Measure with evals and regression checks.
Eval-First Loop
- Define capability eval and regression eval.
- Run baseline and capture failure signatures.
- Execute implementation.
- 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
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/affaan-m/everything-claude-code
- Category
- AI & Agent Building
More from affaan-m/everything-claude-code
All 256- Cost Aware Llm Pipeline5.4K
- Django Verification5.4K
- Springboot Verification5.4K
- Codebase Onboarding5.3K
- Deep Research5.3K
- Rust Testing5.3K
- Ai First Engineering5.2K
- Autonomous Loops5.2K
- Content Engine5.2K
- Content Hash Cache Pattern5.2K
- Kotlin Coroutines Flows5.2K
- Swiftui Patterns5.2K
- Investor Materials5.1K
- Laravel Tdd5.1K
- Regex Vs Llm Structured Text5.1K
- Compose Multiplatform Patterns5K
- Continuous Agent Loop5K
- Foundation Models On Device5K
- Investor Outreach5K
- Kotlin Patterns5K
- Rust Patterns5K
- Swift Actor Persistence5K
- Swift Protocol Di Testing5K
- Bun Runtime4.9K
Recommended
More AI & Agent Building
team-agent-orchestrationaffaan-m/eccRun team-based orchestration for agent squads using work items, ownership, agent Kanban, merge gates, and control pane handoffs.5.1Kskills.sh installsregex-vs-llm-structured-textaffaan-m/everything-claude-coderegex vs llm structured text5.1Kskills.sh installs
avoid-ai-writingconorbronsdon/avoid-ai-writingAudit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI 5.1Kskills.sh installs
agent-slackstablyai/agent-slackSlack CLI for agents: read URLs/threads/history/unreads/later/canvases/workflows, create canvases from Markdown, search messages/files, download attachments, lo4.8Kskills.sh installs