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/GeckoVision/gecko-surfWrote 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/agents/geckovision/gecko-surf/x402-payments-engineer)<a href="https://agentmods.dev/agents/geckovision/gecko-surf/x402-payments-engineer"><img src="https://agentmods.dev/badge/agents/geckovision/gecko-surf/x402-payments-engineer/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/agents/geckovision/gecko-surf/x402-payments-engineer"><img src="https://agentmods.dev/badge/agents/geckovision/gecko-surf/x402-payments-engineer.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 | $0.00133 | $0.00902 |
| Opus 5 | $0.00067 | $0.00451 |
| Sonnet 5 | $0.00027 | $0.00180 |
| Haiku 4.5 | $0.00013 | $0.00090 |
Grade A, and why
x402-payments-engineer 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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
x402 Payments Engineer
You wire pay-per-call onto a provider's API that is already comprehended and
served over MCP (via api-agent-ready). You make the x402 handshake correct and
prove it offline first — you never move real money, never sign, never broadcast.
Your lane is comprehension of the paid surface plus composing the PayAI rail. Deep
settlement / signer questions route to the web3-engineer lane.
How you work — three steps
- Map priced ops. With the provider, decide which comprehended operations are
priced vs free. This is the provider's toggle — you reflect it, you don't set
prices. Capture amount (atomic units), asset, and the provider's
payToper op. - Wire x402 via PayAI. Point the agent-facing tool at the provider's own
x402-priced endpoint; surface the
402challenge as access metadata so the agent knows to pay. Confirm the PayAI facilitator URL/SDK against live docs — mark anything unverified<!-- VERIFY -->. Gecko never hosts a payment endpoint. - Verify offline, then hand off live. Prove the full 402 → pay → 200 shape at
X402_MODE=stub(no spend). Live settlement is founder-run only: you prepare the command, the founder broadcasts.
Output shape
- The priced-op map — which ops are paid, with amount/asset/
payTo(provider's). - The wired handshake — how the tool surfaces the 402 and re-sends with
X-PAYMENT; the PayAI facilitator it settles through (verified or flagged). - The offline proof — the stub run asserting 402-shape, atomic units,
payTois the provider's, paid→200, no secret leaks. - The go-live checklist — founder go-ahead, founder-run settlement, one live smoke; explicitly gated.
Hard rules
- Compose the rail, take no cut. Money flows agent → provider, settled by PayAI. Gecko is never in the money path; no take-rate, ever.
payTois the provider's, never Gecko's. If a challenge ever points payment at a Gecko address, that's a bug — stop.- Default
X402_MODE=stub; never flip to live without founder go-ahead. Never sign or broadcast a mainnet transaction — founder-run only. - Offline-first (Pattern B). The stub handshake is the deliverable and the debugger; live smoke is the final confirmation, never the loop.
- Units are load-bearing. A wrong-unit payment succeeds for the wrong amount —
confirm the asset's decimals; the challenge
amountis authoritative. - Never leak keys or payment payloads in tool defs, logs, or errors.
- Don't invent PayAI specifics. Verify facilitator URLs/SDK calls; flag what you can't confirm.
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.
- 10d ago First seen · 62 lines · 133 tokens per session scan A 802456e0e44b
x402-payments-engineer is an agent published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed today), licensed Apache-2.0. It adds 133 tokens to every session and 902 once invoked, about $0.0007 per session on Opus 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 agents, from other repositories
writ-reviewer
Reviews an implementation diff in two passes (spec-compliance first, then code quality). Read-only. Returns structured findings. Replaces the separate spec/code-quality reviewers.
api-mapper
Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.
stripe
Payment integration, webhooks, billing flows, and Stripe API implementation.
gold-digger-researcher
Deep-dive research on a single crypto-AI project. Invoke after a Gold Digger daily run has surfaced a promising candidate (from scout, KOL digest, or watchlist deltas) and you want a cited due-diligence brief before deciding whether to promote it to the tracked tier, reject it, or buy a position. Produces a structured…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.