Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/x402agent/solana-clawd/clawdex)<a href="https://agentmods.dev/skills/x402agent/solana-clawd/clawdex"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/clawdex.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.01925 |
| Opus 5 | $0.00024 | $0.00962 |
| Sonnet 5 | $0.00010 | $0.00385 |
| Haiku 4.5 | $0.00005 | $0.00193 |
Grade B, and why
clawdex scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Default model**: `gpt-5.3-codex` (set in `~/.codex/config.toml`) How it starts
The opening of the file, as written. The whole thing — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clawdex
Claude Code plans and reviews. OpenAI Codex executes fast. Browser Use handles the web. Upstash Boxes isolate the compute.
Install
# Codex CLI (bux installs this automatically)
npm install -g @openai/codex
# Or from a Clawdbot session:
/plugin install codex@openai-codex
Verify:
codex --version
claude --version
browser-harness-js --version 2>/dev/null || echo "browser-harness via BUX"
Architecture
User prompt
│
▼
Claude Code (claude-sonnet-4-6) ← you are here: reason, plan, review
│
├── codex exec "..." ← fast code gen / repetitive tasks
│
├── browser-harness-js ← web research, UI testing (BUX browser box)
│
└── box.exec.command(...) ← run in Upstash compute sandbox
Each Clawdex run lives in an Upstash Box — ephemeral, isolated, with a box-local Solana wallet and the OpenClawd framework pre-seeded at /work/openclawd-framework.
Quick Start
One-shot task (box run)
# Via the box API
POST /api/box/run
{
"boxId": "your-box-id",
"prompt": "Build a TypeScript CLI that fetches SOL price from Birdeye",
"agentHarness": "clawdex",
"agentModel": "anthropic/claude-sonnet-4-6"
}
Streaming task (SSE)
POST /api/box/stream
{
"boxId": "your-box-id",
"prompt": "Audit the pump SDK for rug pull vectors",
"agentHarness": "clawdex"
}
Shell (PTY mode, bux box)
# Claude Code as the harness, Codex available as a tool
bash pty:true workdir:~/project command:"claude 'Build a DeFi dashboard, use codex for boilerplate'"
# Or dispatch directly to Codex for speed
bash pty:true workdir:~/project command:"codex exec --full-auto 'Generate Jupiter swap wrapper with error handling'"
Dual-Engine Dispatch Pattern
Claude Code is the orchestrator. Codex is the executor. Use this pattern:
1. Claude: plan + architecture
2. Claude → codex exec "implement <component>"
3. Claude: review Codex output
4. Claude → codex exec "write tests for <component>"
5. Claude: final review + integration
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 253 lines · 49 tokens per session scan B eb8b30b6b5a5
clawdex is a skill published in the GitHub repository x402agent/solana-clawd (24 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,925 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…