opendexter

opendexter is a skill for Claude Code from Dexter-DAO/opendexter-ide. It costs 28 tokens per session (4,808 once invoked), scanned A, original, MIT.

Instructions for using OpenDexter, a hosted service for wallet balances, assets, transfers, trades, and paid APIs. Its MCP connection links the current client session to the user's Dexter Wallet without exposing private keys.

In plain words
What is it for?
Use them to check wallet readiness and balances, view assets, find deposit details, and handle supported send, buy, sell, payment, and wallet-gated API requests.
Why use it?
They provide the required order of wallet checks and authentication steps for financial actions while keeping the supported hosted workflow separate from the local version.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument; mentions Claude Code; mentions Codex.

Part of the opendexter plugin — 3 skills, 1 MCP server shipped together

Good fit Use them to check wallet readiness and balances, view assets, find deposit details, and handle supported send, buy, sell, payment, and wallet-gated API requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dexter-dao/opendexter-ide/opendexter
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Dexter-DAO/opendexter-ide --skill opendexter
Clone the repo
git clone --depth 1 https://github.com/Dexter-DAO/opendexter-ide

Made for: Claude Code.

Or install opendexter, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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.

agentmods badge for opendexter

README.md
[![agentmods](https://agentmods.dev/badge/skills/dexter-dao/opendexter-ide/opendexter/github.svg)](https://agentmods.dev/skills/dexter-dao/opendexter-ide/opendexter)
Your own site
<a href="https://agentmods.dev/skills/dexter-dao/opendexter-ide/opendexter"><img src="https://agentmods.dev/badge/skills/dexter-dao/opendexter-ide/opendexter/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for opendexter

Your own site · 80×15
<a href="https://agentmods.dev/skills/dexter-dao/opendexter-ide/opendexter"><img src="https://agentmods.dev/badge/skills/dexter-dao/opendexter-ide/opendexter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,808 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00028 $0.04808
Opus 5.5 $0.00011 $0.01923
Sonnet 5.5 $0.00006 $0.00962
Haiku 4.5 $0.00003 $0.00481

Measured 12d ago against content hash 739ea7a24d59, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

opendexter scanned grade A with 0 findings 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 12d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

opendexter-plugin/skills/opendexter/SKILL.md · 370 lines

How it starts

The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenDexter

OpenDexter is Dexter's hosted financial-action layer at https://open.dexter.cash/mcp. Native MCP OAuth binds the current client session to the user's Dexter Wallet. The model receives no private key or passkey.

This is the canonical hosted OpenDexter workflow shared by ChatGPT, Codex, and Claude Code. Keep every live capability and complete user journey available here in this guide as the product grows. Feature sections below are parts of that one guide, not separate Buy, Sell, Send, credit, wallet, or recovery micro-skills.

Use the current client's native Connect or MCP login action described in references/authentication.md. Do not substitute local npm-proxy commands or advertise a capability that the hosted tool roster does not ship. The local seven-tool npm/stdio edition is intentionally a separate workflow. OAuth must complete before MCP initialization and tool discovery. Every hosted tool uses the same vault OAuth scope.

Finish the user's task

Use the current request, earlier instructions, relevant preferences and active wallet permissions together. Proceed when they cover the action and cost. Ask only for missing information, a material choice or missing permission. A tool boundary, HTTP method or input field alone is not a reason to ask again. Runtime spending and permission checks still apply.

Lead with the useful result. After a trade, report actual receipt amounts and read current holdings when useful. After a service call, deliver its answer or artifact even while payment observation is pending, and state that pending status separately. Complete ordinary follow-up reads under the existing task. Keep exact receipt evidence available without dumping hashes and raw units in the customer reply. Preserve small nonzero charges and partial data.

Recognize ordinary requests

  • "Do I have a Dexter Wallet?", "what is my balance?", or "where can I add funds?": call dexter_wallet first.
  • "What is in my wallet?", "what can I do with my assets?", or "what can I send, buy, or sell?": call dexter_wallet first, then dexter_wallet_portfolio. Compose cash/readiness and asset inventory without treating either as execution authority.
  • "What can Indexter do?", "show me Apify offerings", or "find an API for this job": call indexter_search once with the task resolved from conversation context. Discovery never pays and does not require a separate wallet call.
  • "What will this API cost?" or a known paid URL: call x402_check; checking is not permission to pay. A check may affect the provider; use current task authority for its consequence and ask only if that authority is missing.
  • "Pay for/call this API": discover or check first, disclose the exact terms, and use the purchase flow below. Resolve terms from the conversation and fresh tools; ask only for a missing decision needed to cover the consequence.

Read the full file on GitHub · 370 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago Changed 739ea7a24d59
  2. 1mo ago Changed · +56 lines · +3 tokens per session a830e6928f2c
  3. 1mo ago Changed · +68 lines 77d6e43edfa7
  4. 2mo ago Changed · +71 lines · -76 tokens per session bd34c1584f34
  5. 2mo ago First seen · 175 lines · 101 tokens per session scan A 9aedac33c664

Subscribe to this mod's changes

opendexter is a skill published in the GitHub repository Dexter-DAO/opendexter-ide (2 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 4,808 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

opendexter compared with skills from other repositories

opendexter next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
opendexterDexter-DAO/opendexter-ideSkill28d agoMITA28Claude Code
serasera-cx/sera-agentsSkill202d agoMITA24Claude Code, Codex
serasera-cx/sera-agentsSkill202d agoMITA90Claude Code, Codex
x402aomi-labs/skillsSkill82d agoMITA84Claude Code
sera-protocolsera-cx/sera-agentsSkill202d agoMITA58Claude Code, Codex
gentech-x402-servicesGentech-Labs/genTech-agent-kitSkill016d agoMITA99Claude Code, Codex
before-you-paynock-for-mak/skillsSkill02mo agononeA96Claude Code, Codex