tmdgusya/engineering-discipline

1

karpathy Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and…

tmdgusya/engineering-discipline

51

2

run-plan Use when you have a written implementation plan to execute. Loads the plan, reviews critically, executes tasks in dep…

tmdgusya/engineering-discipline

49

3

clarification Use when a user's request is vague, ambiguous, or underspecified.

tmdgusya/engineering-discipline

48

4

clean-ai-slop Corrective cleanup of AI-generated code — removes LLM-specific patterns while preserving behavior.

tmdgusya/engineering-discipline

47

5

plan-crafting Use when a task's scope is clear and multi-step implementation is needed, before touching code. Triggered after clari…

tmdgusya/engineering-discipline

46

6

rob-pike Rob Pike's 5 Rules of Programming — a decision framework that prevents premature optimization and enforces measuremen…

tmdgusya/engineering-discipline

46

7

systematic-debugging Use when encountering any bug, test failure, or unexpected behavior. Enforces a strict reproduce-first, root-cause-fi…

tmdgusya/engineering-discipline

46

8

long-run Orchestrates multi-day execution of complex tasks through milestones.

tmdgusya/engineering-discipline

44

9

review-work Use after run-plan completes to independently verify the implementation. Reads only the plan document and inspects th…

tmdgusya/engineering-discipline

44

10

milestone-planning Decomposes complex, multi-day tasks into optimized milestones (ultraplan).

tmdgusya/engineering-discipline

43

11

simplify Review changed code for reuse opportunities, quality issues, and inefficiencies using three parallel review agents, t…

tmdgusya/engineering-discipline

41