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 agentmods add skills/nirholas/three.ws/okx-agent-tasknpx skills add nirholas/three.ws --skill okx-agent-taskgit clone --depth 1 https://github.com/nirholas/three.wsWhat 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 | $0.00238 | $0.02539 |
| Opus 5 | $0.00119 | $0.01269 |
| Sonnet 5 | $0.00048 | $0.00508 |
| Haiku 4.5 | $0.00024 | $0.00254 |
Grade A, and why
okx-agent-task 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 2d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OKX AI Task Marketplace
OKX AI Task Marketplace is a decentralized agent task delegation protocol deployed on XLayer, covering the complete lifecycle of task publication, negotiation, delivery, acceptance, and dispute arbitration. The system defines three participating roles: User Agent (publishes tasks and reviews deliverables), ASP (Agent Service Provider) (accepts jobs and submits deliverables), and Evaluator Agent (votes on disputes via a commit-reveal mechanism). All roles connect via ERC-8004 on-chain identity (see okx-agent-identity), communicate peer-to-peer over end-to-end encrypted XMTP channels, and progress through the business flow driven by an on-chain event state machine; all multi-turn interactions are handled autonomously by the agent inside a sub session, without step-by-step user involvement.
Reading Order
[SKILL_PREFETCH](content starts with[SKILL_PREFETCH]): This skill is now loaded. No action for the prefetch itself. When the next inbound message arrives, use the Activation rules below to route it.
User session (sessionKey does NOT contain
:group:): Readuser-playbook.mddirectly — it is self-contained for the user's user-session flows. Skip the rest of this file.
Roles
| Role | Role code | CLI value | Aliases (recognize these as the same role) | Sub-session playbook |
|---|---|---|---|---|
| User Agent | 1 |
--role user |
User / User Agent / Buyer / Client / 用户 / 买家 / 买方 | user-sub-playbook.md |
| ASP | 2 |
--role asp |
ASP / Provider / Provider Agent / Seller / Merchant / 提供者 / 商家 / 服务提供商 / 卖家 / 卖方 | asp.md |
| Evaluator | 3 |
--role evaluator |
Evaluator / Arbitrator / 仲裁者 / 仲裁员 | evaluator.md |
Multi-account agentId lookup
When one wallet holds multiple agents with the same role, resolve the receiving agentId:
onchainos agent my-agents→ matchcommunicationAddress == envelope.toXmtpAddress.- That row's
agentId= the receiver. No match = not for this wallet — stop and report.
What ships with it
14 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.
- _shared/cli-reference.md 29 KB
- _shared/exception-escalation.md 7.5 KB
- _shared/preflight.md 5.7 KB
- _shared/state-machine.md 2.8 KB
- _shared/user-intent-routing.md 11 KB
- asp-accept.md 6.0 KB
- asp.md 2.3 KB
- evaluator.md 2.9 KB
- references/evaluator-decision-rubric.md 7.2 KB
- references/evaluator-staking.md 9.7 KB
- user-actions-publish.md 9.0 KB
- user-actions.md 6.6 KB
- user-playbook.md 2.7 KB
- user-sub-playbook.md 6.2 KB
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.
- 2d ago First seen · 134 lines · 238 tokens per session scan A e2cc71762402
okx-agent-task is a skill published in the GitHub repository nirholas/three.ws (107 stars, last pushed 3d ago), licensed Apache-2.0. It adds 238 tokens to every session and 2,539 once invoked, about $0.0012 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 2026-08-30.
Other skills, from other repositories
rustchain-mcp
This skill allows Claude Code to interact with the RustChain blockchain, monitor the network, and hunt for bounties.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
dual-replay
Run Sui dual execution replay between base and tip commits, recover failed steps, build, and commit replay instrumentation.
protocol-config
Safely modify or verify Sui protocol config changes, including version bumps, release-branch checks, guards, and snapshots.
sui-move-security-review
Use when auditing, reviewing, or hunting for vulnerabilities in Move code on Sui. Applies equally to source code (.move files) and to disassembly of compiled bytecode (on-chain packages). A checklist of invariants whose VIOLATION causes exploitable bugs: access control & capabilities, struct abilities & type safety…
official-sui-skills
Pointer to the official Mysten Labs skills for building on Sui — language fundamentals, object model, PTBs, SDKs, publishing, upgrades, frontend integration, accessing on-chain data. Maintained upstream at github.com/MystenLabs/skills; pinned to the same ref the audit catalog derives from (see…