Primary execution path for PumpGrok. Obtain the best route via Jupiter, set slippage and priority fees, verify exact parameters against the approved ticket, and prepare a single-send transaction. Used only by SNIPER and EXIT.
Scanned 9/12/2026
Install to Claude Code
npx -y skills add swcstudiospace/PumpGrok --skill jupiter-routing --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Jupiter Routing?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/swcstudiospace-jupiter-routing)More formats (shields.io, HTML) on the badges page.
---
name: jupiter-routing
description: Primary execution path for PumpGrok. Obtain the best route via Jupiter, set slippage and priority fees, verify exact parameters against the approved ticket, and prepare a single-send transaction. Used only by SNIPER and EXIT.
---
# Jupiter Routing
## Purpose
Execute the single approved buy (or later sell) with the best available price and controlled risk.
## Preferred Tool Path
```bash
python /workspace/pumpgrok/tools/jupiter_quote.py \
--input-mint <INPUT> --output-mint <OUTPUT> --amount <LAMPORTS> --slippage-bps <BPS>
```
Also estimate fee:
```bash
python /workspace/pumpgrok/tools/priority_fee.py --multiplier 1.25 --max-micro 50000
```
## Preconditions (ALL must be true)
1. RISK Verdict = CLEAR (or CONDITIONAL conditions met)
2. Explicit human message containing ticket ID + mint + size + max slippage
3. CHIEF confirmation that daily-loss limit is not breached
4. Live quote obtained within the last 30–60 seconds
## Rules
- Submit once only
- On any timeout or unknown result → do NOT retry; report “UNKNOWN RESULT – reconcile by signature”
- Immediately hand the filled position to RUG + EXIT
## Never
- Retry without a new human approval
- Change size or mint
- Execute on a different token than approved
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling