Three-perspective preflight review skill (MELCHIOR/BALTHASAR/CASPAR personas, parallel Task spawn) for high-stakes changes — front-loads post-hoc optimization insights before walltime / cost / destructive state is committed. Triggers on walltime >= 2h, >= 100M row DML, non-reversible cutover, new pipeline layer, >= $10 spend, or long-poll scripts.
5 skills
Behavioral craft skills distilled from obra/superpowers (MIT): skill-tdd (author skills via RED-GREEN-REFACTOR pressure testing, with a structural-first entry gate), atomized-briefing (context-free 2-5 min task plans for formation workers / subagent dispatch), root-cause-debugging (Iron Law + 3-failed-fixes escalation to dual-magi-review). Superpowers teaches, harness enforces — this plugin is the explicitly-behavioral annex wired into the enforcing half.
4 skills
Peer-pane Claude Code worker orchestration via tmux + jsonl mailbox. Bundles Formation worker spawning, session-scoped routing, and a receipt-gated babysit-pr skill for bounded CI monitoring and reply-only review follow-up. Hooks suggest Formation and mint local ownership receipts only for active Formation sessions.
2 skills · 1 agent · hooks
Bounded Magi pre-flight, Dual-Magi design, and Ultramagi implementation review profiles for Codex.
3 skills · hooks
Three defense-in-depth hooks: credential value scrub (PostToolUse), admission keyword reminder (UserPromptSubmit), bash command guard (PreToolUse). Built after repeated credential leak incidents — structural fix when behavioral rules in CLAUDE.md keep failing.
1 skill · hooks
Operational safety rails for long-running operations. Pre-flight algorithm fitness CLI (working set vs RAM ceiling, with concrete alternatives), in-flight heartbeat helper + cron watcher (stale + ETA overrun detection), Discord + gh issue auto-emit. Human-in-loop only — no auto-kill. Built after a 23h sunk-cost incident where philosophy-level early-bleeding-detection lived only in CLAUDE.md memory, not in structural rails.
1 skill · hooks