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.
Plugin harness-magi from marketplace claude-harness in hrmtz/claude-harness. Commands read from the repo's manifest — 1 month ago.
bug-huntAdversarial post-change review. Spawn three parallel Task agents focused on distinct bug categories — race / concurrency, edge-case / null-empty, and error-swallow / silent-failure — to surface defects that linear self-review systematically misses. The siblings of magi (pre-flight) and code-review (
dual-magi-reviewIndependent multi-perspective peer review for large design docs. Spawn 3 same-family sub-agent reviewers AND a cross-family reviewer (= different model family、 default: codex-exec) to cancel shared training-data bias. Cross-family is **default mandatory** since v0.6.0 (= gh #195 incident: 4 Claude s
magi-battleRed-vs-blue adversarial team battle over a design that has already reached dual-magi PLATEAU. Red team builds the strongest attacks (chaining the DEFERRED / low-severity findings review filed away one-by-one), blue team defends from the design + rationale, a cross-family blinded judge scores who won
magiContract mirror for the three-perspective preflight review used before high-stakes changes. This Claude surface is an explicit fail-closed availability boundary until a Claude-native structural runner ships; it must not claim deterministic reviewer independence from prose alone. USE WHEN any one tri
ultramagiEnd-to-end rigor loop for a non-trivial, hard-to-reverse change: local plan/design → reversibility-classified briefing → bounded code/measurement → dual-magi/bug-hunt before each irreversible boundary → code-review → next. A superset of dual-magi-review that drives the WHOLE lifecycle, not just one
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
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · hooks
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
72 skills · 72 commands · 64 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.