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.
npx skills add Dexter-DAO/opendexter-ide --skill x402-discoverablegit 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/skills/dexter-dao/opendexter-ide/x402-discoverable)<a href="https://agentmods.dev/skills/dexter-dao/opendexter-ide/x402-discoverable"><img src="https://agentmods.dev/badge/skills/dexter-dao/opendexter-ide/x402-discoverable/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/skills/dexter-dao/opendexter-ide/x402-discoverable"><img src="https://agentmods.dev/badge/skills/dexter-dao/opendexter-ide/x402-discoverable.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 | $0.00115 | $0.01325 |
| Opus 5.5 | $0.00046 | $0.00530 |
| Sonnet 5.5 | $0.00023 | $0.00265 |
| Haiku 4.5 | $0.00012 | $0.00133 |
Grade A, and why
x402-discoverable 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make an x402 API discoverable
Use opendexter audition to discover and register an x402 API's routes in the
OpenDexter / x402gle catalog. A server origin registers routes. A specific
endpoint URL requests an immediate test that can pay the endpoint, evaluate
its response, and save a score. Registration and scoring are separate outcomes.
audition requests a server-side merchant test and can cause paid provider
calls and catalog changes. It does not load a local signer or spend through the
connected user's governed OpenDexter authority. Obtain explicit approval for
the audition itself.
OpenDexter's platform verifier funds the test. Funding the seller's connected wallet does not fund this command. Check the returned result to see whether the test completed.
When this skill applies
Use it when the user's API already returns HTTP 402 with a valid payment manifest. Use the x402-server skill first if the API still needs its paywall.
The one command
npx @dexterai/[email protected] audition <server-url> --json
- Pass a server origin to discover and register its routes without an immediate paid test.
- To request an immediate test, pass a specific endpoint URL.
- Use
--jsonwhen an agent needs the structured result. Omit it for a human reading the summary. Add--verbosefor request references and HTTP response metadata on stderr.
No global install is needed; this command requests the exact pinned package version.
Discovery requirements
The audition finds paid routes three ways, in order of preference:
- OpenAPI 3.1 document at
/openapi.json(preferred), withinfo.x-guidance, arequestBodyschema per paid operation, and anx-payment-infoblock carryingprotocols(x402 and/or mpp) and a structuredprice. /.well-known/x402, a descriptor listing the paid routes.- A bare probe of a URL that returns HTTP 402 with a valid payment manifest.
If discovery returns discovery_failed, read its message and warnings. Check
that the advertised discovery document is reachable and describes the routes.
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 2600c7f74ac1
- 1mo ago Changed · +13 lines 70136959de41
- 1mo ago Changed 74d2378b49fc
- 1mo ago Changed db9a36ad3efd
- 2mo ago First seen · 117 lines · 115 tokens per session scan A b4377f9a9d4e
x402-discoverable is a skill published in the GitHub repository Dexter-DAO/opendexter-ide (2 stars, last pushed 8d ago), licensed MIT. It adds 115 tokens to every session and 1,325 once invoked, about $0.0005 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.
x402-discoverable compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| x402-discoverableDexter-DAO/opendexter-ide | Skill | 2 | 8d ago | MIT | A | 115 | Cursor |
| serasera-cx/sera-agents | Skill | 20 | 2d ago | MIT | A | 24 | Claude Code, Codex |
| serasera-cx/sera-agents | Skill | 20 | 2d ago | MIT | A | 90 | Claude Code, Codex |
| x402aomi-labs/skills | Skill | 8 | 2d ago | MIT | A | 84 | Claude Code |
| trustlayer-sybil-scannerBankrBot/skills | Skill | 1.2k | 2d ago | none | A | 43 | Claude Code, Codex |
| sera-protocolsera-cx/sera-agents | Skill | 20 | 2d ago | MIT | A | 58 | Claude Code, Codex |
| agent-registrylxyeternal/MalSkillBench | Skill | 64 | 4d ago | none | A | 78 | Claude Code, Codex |