adr
Architecture decision records: durable decisions with their date, context, and consequences — supersede, never rewrite.
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
> /plugin marketplace add azrtydxb/procoder > /plugin install procoder@procoder
How it fires
How this command gets triggered: by you, by Claude, or both.
/simplifyContext preview
What this command does when you run it.
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
description: "The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut."
The user invoked /procoder:simplify with arguments:
The launcher is: "${CLAUDE_PLUGIN_ROOT}/hooks/launcher.sh"
This review hunts one thing only: code that should not exist. Correctness bugs, security, performance — out of scope here; those belong to `launcher.sh check`, `security`, and /procoder:debug.
Scope: with no arguments, review the working-tree diff (`git diff` plus staged). With `repo` (or a path) in the arguments, sweep that whole scope — use `launcher.sh index unused` and `launcher.sh maintain` as starting evidence, then read.
The diff pass runs before every pull request; the repo sweep before a tag.
Every finding is one line, with a mandatory replacement — a finding without a replacement is hedging, not reviewing:
<file>:L<line>: <tag> <what>. <replacement>.
The five tags:
Replacement: nothing.
function.
(CSS over JS, a DB constraint over app code). Name the feature.
layer with one caller.
End with the score line: `net: -<N> lines possible.` — and when there is genuinely nothing to cut, say exactly `Lean already. Ship.` and stop; never invent findings to look thorough.
Rules:
minimum check is part of the code, not decoration (see /procoder:tdd).
`launcher.sh debt`) is a recorded decision, not a finding — unless its revisit trigger has arrived.
decides — P-CONTROL applies to reviews too.
Senior-developer discipline for AI coding agents. A commit gate that counts unchecked as failing, quality controllers that refuse to call unfinished work done, and a lessons loop that closes each escaped bug's class. One Go binary, no runtime deps, works with 20+ agents.
Architecture decision records: durable decisions with their date, context, and consequences — supersede, never rewrite.
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
Run the formatting gate over the changed files, as a commit or CI would.
CI/CD hygiene and run health: pinned actions, timeouts, concurrency, tests — plus the latest runs via gh.
Copilot's auto-review escapes: find them since the last look, sanitise them, and turn each one into a lesson.