implement

Implementation

Verification-driven coding with tight feedback loops. Distilled from 21,321 tracked operations across 64+ projects, 612 debugging sessions, and ~600 transcribed working sessions from the Apr-Jul 2026 corpus. These are the patterns that consistently ship working code.

Core insight: Verify in tight loops, roughly every 2-3 edits. 73% of fixes go unverified across the dataset, the single biggest quality gap. And proof lives where the artifact is consumed, not where it was produced: green producer gates are necessary, never sufficient.

How to read this skill: the loop and the heuristics below are calibrated for non-trivial implementation work. Trivial fixes (config, typo, single-line) shouldn't drag through five phases. Use judgment, scale planning to scope, and skip what doesn't apply. The Code Discipline section is principles that bias toward caution; for one-line changes, just make the change.

The Loop

Implementation work composes from five things that must all be true by the time a chunk ships. Not a fixed order; the graph below shows the natural dependencies and the loop-backs that are routine in practice.

digraph implement {
    rankdir=LR;
    node [shape=box];

    "ORIENT" [style=filled, fillcolor="#e8e8ff"];
    "PLAN" [style=filled, fillcolor="#fff8e0"];
    "IMPLEMENT" [style=filled, fillcolor="#ffe8e8"];
    "VERIFY" [style=filled, fillcolor="#e8ffe8"];
    "COMMIT" [style=filled, fillcolor="#e8e8ff"];

    "ORIENT" -> "PLAN";
    "PLAN" -> "IMPLEMENT";
    "IMPLEMENT" -> "VERIFY";
    "VERIFY" -> "IMPLEMENT" [label="fix", style=dashed];
    "VERIFY" -> "COMMIT" [label="pass"];
    "COMMIT" -> "IMPLEMENT" [label="next chunk", style=dashed];
}

• Oriented. Existing code is read before anything gets touched. Grep → Read → Read is the dominant opening across the dataset. Sessions that read 10+ files before the first edit require fewer fix iterations downstream. Blind changes are the most expensive way to start. Before creating any new structure (module, config surface, CLI group, error type), locate the nearest in-repo exemplar and clone its shape; the repo usually solved this kind of thing once already.