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.
git clone --depth 1 https://github.com/Dexter-DAO/opendexter-ideWrote 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/rules/dexter-dao/opendexter-ide/x402-coding)<a href="https://agentmods.dev/rules/dexter-dao/opendexter-ide/x402-coding"><img src="https://agentmods.dev/badge/rules/dexter-dao/opendexter-ide/x402-coding/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.
<a href="https://agentmods.dev/rules/dexter-dao/opendexter-ide/x402-coding"><img src="https://agentmods.dev/badge/rules/dexter-dao/opendexter-ide/x402-coding.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00780 | $0.00780 |
| Opus 5.5 | $0.00312 | $0.00312 |
| Sonnet 5.5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
x402-coding 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 1mo 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.
What it actually says
x402-coding:
- Current OpenDexter source registers eight tools before connection. Published
1.24.1exposes seven;dexter_report_workis the added source tool. - Keep the two execution models separate:
- OpenDexter is a local proxy to a hosted governed runtime. It uses a stored OAuth bearer for account-bound tools and never uses a local signer or fallback.
@dexterai/x402is an independent application SDK. Its wallet adapters or application-owned keys do not inherit OpenDexter identity, authority, or limits and must never be substituted for a blocked OpenDexter operation.
- For OpenDexter, use exactly this flow:
x402_search→x402_check→ review and approval →x402_fetchwith onlyintentIdandmaxAmountAtomic. - Keep
intentIdopaque. It is server-owned and binds the exact request and seller terms. Never reconstruct or replace it. - After an uncertain fetch, call
x402_statuswith the sameintentId. Never auth-refresh and retry the consequential fetch after possible dispatch. x402_accessis a separate anonymous fresh one-call legacy wallet-proof operation. It is not Dexter OAuth or governed payment authority, preserves no cross-call continuity, and never accepts or persists access-session credentials. A non-GET access request needs separate approval and is never automatically retried.x402_walletanddexter_portfolioare account-bound and require the connected bearer. A balance or portfolio does not prove active governed authority.- Use
dexter_report_workfor meaningful work updates with the stored OAuth bearer bound to the same agent. Reporting needs no spending grant or funding. After rejection or possible dispatch, the proxy does not refresh authentication and resend the report automatically. Keep private data, credentials and control characters out of summaries. Server-assignedobservedAtandexpiresAtdescribe statement freshness. - After an uncertain report response, preserve the same
operationIdand identical fields. On a revision conflict, inspectcurrentReportandcurrentRevision; a deliberate update uses a newoperationIdand thatcurrentRevisionasexpectedRevision. Financial outcomes retain their own receipts. - For a deliberately independent
@dexterai/x402integration, import from subpaths, never from the root package:import { payAndFetch } from '@dexterai/x402/client'import { x402Middleware } from '@dexterai/x402/server'import { useX402Payment } from '@dexterai/x402/react'
- Install the tested V6 pair together:
@dexterai/[email protected]and@dexterai/[email protected], on Node 22 or newer. - Narrow the one-shot SDK's
PayResultonok, thenpaid. Apayment_unconfirmedresult may already have moved money and must not be automatically retried. Do not apply SDK recovery guidance to an OpenDexter fetch. wrapFetchandcreateX402Clientwere removed; never generate them.- Solana SDK payments require
feePayerin the accept'sextrafield. EVM payments do not.
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.
- 1mo ago Changed · +13 lines · +193 tokens per session 10710acb94c4
- 1mo ago First seen · 43 lines · 587 tokens per session scan A 16ade7d7662a
x402-coding is a cursor rule published in the GitHub repository Dexter-DAO/opendexter-ide (2 stars, last pushed 21d ago), licensed MIT. It adds 780 tokens to every session, about $0.0031 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.
Other cursor rules, from other repositories
agent-models
Which model subagents use. Default is the parent's model; the user's most recent instruction overrides it.
research-before-suggesting
Never make up features, APIs, or config options. Research before suggesting technical solutions.
conservative-file-creation
Check for existing files before creating. Be conservative about new files and code.
repository-layout
Canonical map of repo folders and docs.
engineering-standards
Engineering quality — security defaults, show options when planning, think through failure modes.
pn-build-gate
For build/design/scaffold requests, load pn-build or pn-design; discovery and skeptic mandatory. For fix/tweak, use skills directly.