audit-fleet
01Command Claude Code
Parallel attacker-minded audit: fan out one security-auditor per attack surface, each streaming findings to disk, then dedupe/rank and file issues. Usage: /audit-fleet [scope hint].
Cross-chain DEX infrastructure for humans and AI agents — swap tokens across 14 chains via Telegram, WhatsApp, Discord, or a programmatic REST/MCP/A2A API.
Command Claude Code
Parallel attacker-minded audit: fan out one security-auditor per attack surface, each streaming findings to disk, then dedupe/rank and file issues. Usage: /audit-fleet [scope hint].
Command Claude Code
Attacker-minded security audit of scoped files. Traces auth + money-path data flows, streams compact findings incrementally (never one giant end-of-session JSON dump). Usage: /audit [attack-class].
Command Claude Code
Treat one confirmed bug as a class: reproduce, fix, generalize the class, sweep the repo, and fix every instance with one commit each. Usage: /bugclass.
Command Claude Code
Deploy Suwappu services on Railway. Usage: /deploy [prod|dev] [python-api|python-worker|terminal|api-ts|showcase|all].
Command Claude Code
Ship the current changes end-to-end: branch → commit → PR → CI green → merge → verify EVERY service actually deployed and booted → read logs → fix what broke. Usage: /ship [PR title].
Command Claude Code
Check what's actually running: Railway control plane + deep health + logs + CI. Usage: /status [prod|dev] [--quick].
Command Claude Code
Audit every git worktree for uncommitted, unpushed, or stashed work at risk before any reset/merge/cleanup. Usage: /worktree-check.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: