adr
Architecture decision records: durable decisions with their date, context, and consequences — supersede, never rewrite.
The dependency freshness report: what is behind, by how much, per ecosystem — judgment stays yours.
> /plugin marketplace add azrtydxb/procoder > /plugin install procoder@procoder
How it fires
How this command gets triggered: by you, by Claude, or both.
/depsContext preview
What this command does when you run it.
The dependency freshness report: what is behind, by how much, per ecosystem — judgment stays yours.
description: "The dependency freshness report: what is behind, by how much, per ecosystem — judgment stays yours."
The user invoked /procoder:deps with arguments: $ARGUMENTS
The launcher is: "${CLAUDE_PLUGIN_ROOT}/hooks/launcher.sh"
Run:
"${CLAUDE_PLUGIN_ROOT}/hooks/launcher.sh" deps
Each detected ecosystem reports through its native tool (go list -u, npm outdated, cargo-outdated and pip where available — the tools reach the network). Read the report as judgment, not orders: majors need a changelog read before an update, and a NOT-checked line is a gap to mention, never silently a clean bill. Licenses report where a tool exists (go-licenses for Go) and say so honestly where none does. Propose updates as backlog stories or todos — small and often beats big and rare.
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.