adr
Architecture decision records: durable decisions with their date, context, and consequences — supersede, never rewrite.
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
> /plugin marketplace add azrtydxb/procoder > /plugin install procoder@procoder
How it fires
How this command gets triggered: by you, by Claude, or both.
/testContext preview
What this command does when you run it.
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
description: "Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green."
The user invoked /procoder:test with arguments: $ARGUMENTS
The launcher is: "${CLAUDE_PLUGIN_ROOT}/hooks/launcher.sh"
1. Run `launcher.sh test` (add `--coverage` for the percentage where the runner measures it natively; pass paths to narrow Go packages and pytest targets). Every detected ecosystem runs: go test, cargo test, the package.json test script, pytest, gradle/maven. 2. Read the verdicts as given: `ok` passed, `FAIL` names what broke — fix the code or the test, never delete the assertion to get green. `----` means NOT run (no runner, no test script): that is a gap, not a pass — say so when reporting. 3. Exit codes: 0 all green, 1 something failed, 2 nothing could run. 4. With `[test] policy = "block"` in .procoder/config.toml, todo close and backlog story close run this suite and refuse while it is red — the suite being green is part of "done", not a separate favor. 5. Re-run after every fix; report the final verdict lines to the user.
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.