this repo has no description
at main 42 lines 2.4 kB view raw view rendered
1# Agentic Engineering Toolkit 2 3A minimal, portable toolkit of practices, templates, and skills for rigorous AI-assisted development. Built for personal use across any project and any CLI-based agent harness (Claude Code, pi, opencode, etc.). 4 5The goal: have a single, complete setup that can be dropped into any project to enforce disciplined agentic engineering — TDD, adversarial review, fresh contexts, and human-in-the-loop commits — without reinventing the wheel each time. 6 7## Workflow 8 91. **Init** — Set up a repo with `context-init` (project documentation) and `agent-container` (isolated dev environment) 102. **Work** — Launch the agent container with a task, follow the core loop: spec, failing tests, minimal implementation, adversarial review, commit 113. **Maintain** — Review state of work, clean up, update documentation 12 13## Structure 14 15- `skills/` — Portable markdown instruction sets. Each is a self-contained practice (with a `SKILL.md`) that can be loaded into any agent harness. 16- `bin/` — Standalone scripts (e.g., adversarial review via a second model's API). 17 18## The Core Loop 19 20``` 21 Spec ──→ Failing Tests ──→ Minimal Implementation ──→ All Tests Pass 22 ↑ │ 23 │ ↓ 24 │ Adversarial Review 25 │ (fresh context, hostile) 26 │ │ 27 │ ┌─── hallucinating? ──→ DONE (converged) ───→ Commit 28 │ │ 29 └── real findings ──→ Feed back to Builder (fresh session) 30``` 31 32**Exit condition:** When the adversary starts inventing problems that don't exist in the code, you've converged. Ship it. 33 34## Principles 35 361. **Specs are truth.** Tests serve specs. Code serves tests. 372. **Tests before code.** No implementation without a failing test. 383. **Fresh context per task.** Long sessions degrade. Commit and restart. 394. **Different model for review.** Cognitive diversity catches blind spots. 405. **Fresh context per review.** No relationship drift. Every roast is the first roast. 416. **Hallucination = exit signal.** When the adversary makes things up, you're done. 427. **You commit manually.** The agent proposes. You dispose.