What is solana-agent-commerce?

A development guide for adding paid autonomous services to a Solana agent marketplace. It covers seller and verifier roles, payment steps, service personas, and the x402 payment method, where the buyer pays directly before delivery.

Use it to add or change paid agent services, seller behavior, verification gates, procurement through x402, payment rails, or CoralOS marketplace rounds.

It explains the exact message sequence and payment model so new services follow the repository’s real protocol instead of an outdated escrow flow.

solana-agent-commerce — Skill for Claude Code and Codex by trilltino

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 trilltino/solana_coralOS --skill solana-agent-commerce

Clone the repo

git clone --depth 1 https://github.com/trilltino/solana_coralOS

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/trilltino/solana_coralos/solana-agent-commerce/github.svg)](https://agentmods.dev/skills/trilltino/solana_coralos/solana-agent-commerce)

Your own site

<a href="https://agentmods.dev/skills/trilltino/solana_coralos/solana-agent-commerce"><img src="https://agentmods.dev/badge/skills/trilltino/solana_coralos/solana-agent-commerce/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/trilltino/solana_coralos/solana-agent-commerce"><img src="https://agentmods.dev/badge/skills/trilltino/solana_coralos/solana-agent-commerce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,573 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01573
Opus 5.5	$0.00014	$0.00629
Sonnet 5.5	$0.00007	$0.00315
Haiku 4.5	$0.00003	$0.00157

Measured 2mo ago against content hash e32bd34cbac6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

solana-agent-commerce 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 2mo 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.

skills/solana-agent-commerce/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solana Agent Commerce Skill

Use this skill when a builder asks to add or change a paid autonomous service in this repo.

Mental Model

The core CoralOS round (coral-agents/buyer-agent, coral-agents/seller-agent, coral-agents/verifier-agent) runs this exact wire sequence — every verb below is a real message posted on the market thread, not an aspirational diagram:

WANT -> BID -> AWARD -> PAYMENT_REQUIRED -> PAYMENT_PROOF -> PAYMENT_CONFIRMED -> DELIVERED -> VERIFY -> VERIFIED -> SETTLED

Settlement is x402: the buyer pays the seller directly and finally, before delivery. There is no escrow in this path — a seller that takes payment and never delivers keeps it; reputation is the defense, not a refund. Escrow/arbiter Anchor programs still exist and are deployed (examples/txodds/escrow), available as an alternative building block, but coral-agents does not use them — don't describe the core round in terms of ESCROW_REQUIRED/DEPOSITED/RELEASED, those message types no longer exist in protocol.ts.

All the round's messages are typed (format*/parse* pairs) in packages/agent-runtime/src/market/protocol.ts:

Core round messages: WANT, BID, AWARD, VERIFY, VERIFIED.
Payment messages (rail-generic, but this is where the primary settlement lives now): PAYMENT_REQUIRED / PAYMENT_PROOF / PAYMENT_CONFIRMED / SETTLED / REFUNDED. The seller's AWARD reply always uses rail=x402 for the round's primary payment; the SAME message types, with a different reference, also carry the seller's optional upstream-procurement leg (PROCURE_RAIL=x402, packages/payment-runtime/src/procure.ts) — the first PAYMENT_REQUIRED in a round is always the primary leg.
Untyped verbs: DELIVERED has no formatter/parser — seller-agent/buyer-agent build and match it as a plain string. See references/market-protocol.md for exactly how.

Keep business logic separate from payment movement:

Service delivery belongs in seller service modules or harness adapters.
Payment selection belongs in packages/payment-runtime.
Spend and merchant checks belong in policy modules (packages/agent-runtime/src/policy/policy.ts).
Wire-format changes belong in packages/agent-runtime/src/market/protocol.ts.
Auditable proof belongs in the run ledger (packages/agent-runtime/src/ledger/).

Read the full file on GitHub · 70 lines

Files

What ships with it

6 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.

2mo ago First seen · 70 lines · 34 tokens per session scan A e32bd34cbac6

Subscribe to this mod's changes

solana-agent-commerce is a skill published in the GitHub repository trilltino/solana_coralOS (5 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 1,573 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.

E-commerce Web3 and blockchain

solana-agent-commerce next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
solana-agent-commercetrilltino/solana_coralOS	Skill	5	3mo ago	MIT	A	34	Claude Code, Codex
nft-standardswshobson/agents	Skill	42k	yesterday	MIT	A	48	Claude Code
agentic-commerce-forthecultLeoYeAI/openclaw-master-skills	Skill	2.2k	6d ago	MIT	A	106	Claude Code, Codex
nft-standardsrmyndharis/antigravity-skills	Skill	1.9k	23d ago	MIT	A	48	Claude Code, Codex
dutch-auction-patternsccashwell/evm-cortex	Skill	132	14d ago	MIT	A	49	Claude Code, Codex
openseaalchemyplatform/skills	Skill	55	3d ago	MIT	A	175	Claude Code, Codex
moonpay-commercemoonpay/skills	Skill	112	17d ago	MIT	A	28	Claude Code