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/commands/dexter-dao/opendexter-ide/setup-opendexter)<a href="https://agentmods.dev/commands/dexter-dao/opendexter-ide/setup-opendexter"><img src="https://agentmods.dev/badge/commands/dexter-dao/opendexter-ide/setup-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.
<a href="https://agentmods.dev/commands/dexter-dao/opendexter-ide/setup-opendexter"><img src="https://agentmods.dev/badge/commands/dexter-dao/opendexter-ide/setup-opendexter.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 | $0.00020 | $0.00919 |
| Opus 5.5 | $0.00008 | $0.00368 |
| Sonnet 5.5 | $0.00004 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
setup-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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install OpenDexter MCP
Set up the local proxy for OpenDexter's hosted governed x402 runtime. Setup never creates or enables a local payment wallet.
Steps
- Run the guided installer:
npx @dexterai/[email protected] setup
To target one client:
npx @dexterai/[email protected] install --client cursor
Supported client names are cursor, claude-code, codex, vscode,
windsurf, and gemini-cli. Codex uses TOML, so the installer prints its
exact block instead of editing it.
- Connect the proxy to the hosted governed runtime:
npx @dexterai/[email protected] connect
npx @dexterai/[email protected] connect status
The connection stores an OAuth bearer. It does not by itself prove an active
grant. The bearer targets https://open.dexter.cash/mcp with exact requested
scope vault. Dexter's signed top-level dexter_surface token claim is
separate authority evidence, not a requested OAuth scope. Status must report the exact live grant, principal,
limits, remaining capacity, expiry, scopes, active role, and revocation evidence
before payment authority is treated as active.
- Verify
tools/list.@dexterai/[email protected]exposes eight tools, even before connection:
x402_search, x402_check, x402_fetch, x402_status, x402_access,
x402_wallet, dexter_portfolio, and dexter_report_work.
Confirm that the client lists all eight.
Use reporting for meaningful work updates with the stored OAuth bearer bound
to the same agent; it needs no spending grant or funding. Keep private data,
credentials and control characters out of summaries. Server-assigned
observedAt and expiresAt describe statement freshness.
After an uncertain report response, preserve the same operationId and
identical fields. On a revision conflict, inspect currentReport and
currentRevision; a deliberate update uses a new operationId and that
currentRevision as expectedRevision. After rejection or possible dispatch,
the proxy does not refresh authentication and resend the report automatically.
Financial outcomes retain their own receipts.
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.
- 7d ago Changed 7f1520d1b1e7
- 1mo ago Changed de0833596c05
- 1mo ago Changed · +14 lines · -2 tokens per session bf669f03699a
- 1mo ago Changed d20a60477eb1
- 2mo ago First seen · 86 lines · 22 tokens per session scan A 1935f0e4bcb3
setup-opendexter is a command published in the GitHub repository Dexter-DAO/opendexter-ide (2 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 919 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.
setup-opendexter compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-opendexterDexter-DAO/opendexter-ide | Command | 2 | 8d ago | MIT | A | 20 | Claude Code, Cursor |
| rfcluca-mastrostefano/agent-native-setup | Command | 7 | yesterday | MIT | A | 12 | Claude Code |
| t800-startKhar-AG/t-800-agent | Command | 8 | 2mo ago | MIT | A | 0 | Claude Code |
| pn-audit-dataperniemann/pnCore | Command | 0 | 5d ago | MIT | A | 42 | Claude Code, Cursor |
| pn-delightperniemann/pnCore | Command | 0 | 5d ago | MIT | A | 30 | Claude Code, Cursor |
| t800-doctorKhar-AG/t-800-agent | Command | 8 | 2mo ago | MIT | A | 0 | Claude Code |
| t800-bootstrapKhar-AG/t-800-agent | Command | 8 | 2mo ago | MIT | A | 0 | Claude Code |