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.
Hook Claude Code
Runs when a session starts, executing session-preflight.py via python3. From 0xSoftBoi/suwappubot.
Hook Claude Code
Runs before the agent uses a tool for Agent and Task tool calls, executing guard-general-purpose.py via python3. From 0xSoftBoi/suwappubot.
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, executing parse-check.py via python3. From 0xSoftBoi/suwappubot.
Hook Claude Code
Runs when the agent finishes a response, executing session-journal.py via python3. From 0xSoftBoi/suwappubot.
Settings file Claude Code
Agent settings declaring 4 hook events (SessionStart, PreToolUse, PostToolUse, Stop).
Skill Claude CodeCodex
Standing goal: implement every phase of the AEGIS fork/extend plan (docs/plans/aegis-fork-extend.md) until all are shipped and verified. Shows the phase backlog with file:line anchors and how to work it. Usage: /aegis-goal [phase|item].
Skill Claude CodeCodex
One iteration of the showcase design-improvement loop - render the site locally, screenshot desktop + mobile, critique against the taste rubric, fix the top findings, verify the build, commit and push. Use via /loop for continuous improvement, or invoke once for a single pass. Usage: /design-iterate [focus-hint].
Skill Claude CodeCodex
One iteration of the harness self-improvement loop - digest the session journal, pick the single highest-friction pattern, make ONE surgical patch to a harness artifact (CLAUDE.md, a hook, skill, agent, or lessons promotion), pass the lint gate, commit. Run via /loop or a Routine for continuous improvement, or invoke…
Skill Claude CodeCodex
Standing goal: connect every built-but-unwired feature. Shows the audited disconnect backlog (Jul 2026), how to verify each item, and how to keep this list current. Usage: /goal [item].
Skill Claude CodeCodex
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
Skill Claude CodeCodex
End-of-task reflection - mine THIS session for corrections and friction, then make surgical bounded edits to lessons.md (and only lessons.md). Use at the end of a task, after the user corrected you, or when invoked as /reflect.
Skill Claude CodeCodex
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
MCP server Claude CodeCodexCursor +2
Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.
Instructions file CodexOpenCode
AGENTS.md instructions for 0xSoftBoi/suwappubot, covering agents.md — executable agent policy, ground rules, repo skills (reuse before building), where things live and knowledge base.
Instructions file
Claude Code instructions for 0xSoftBoi/suwappubot, covering claude.md, workflow, response length, git conventions and git operations.
Agent
Autopilot is a trading agent that decides, commits, trades and publishes on its own. It runs on the execution infrastructure we already had (multi-chain swap routing, managed wallets, policy gates, token security) and adds the part that was missing: a loop that forms a thesis, refuses or takes the trade against…
Agent
The control plane gates fund-moving agent calls (POST /v1/agent/swap, POST /v1/agent/swap/execute, and the MCP executeswap tool) through a shared evaluator, PolicyService.evaluate(), before any transaction is built or broadcast. Read-only MCP tools (quotes, portfolio, prices, etc.) are not policy-gated — only…
Skill Claude CodeCodex
Use Suwappu's hosted MCP server for cross-chain quotes, swap simulation and unsigned transaction preparation, managed-wallet portfolio reads, prices, prediction-market research, Hyperliquid research, and Morpho market data.
Skill Claude CodeCodex
Build with the Suwappu REST API: cross-chain quotes, simulation, self-custody or managed swaps, managed-wallet portfolio/prices, Polymarket research and orders, Hyperliquid market research, and Morpho lending-market research.
MCP server Claude CodeCodexCursor +2
Cross-chain DEX for AI agents. Swap tokens across 7+ chains. Runs locally from the @suwappu/mcp-server npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "mini-plus-agent-kit" as configured in 0xSoftBoi/mini-plus-agent-kit. Runs locally from the mini-plus-agent-kit Python package.