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/mission69b/t2000/t2000-setupnpx skills add mission69b/t2000 --skill t2000-setupgit clone --depth 1 https://github.com/mission69b/t2000Wrote 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/mission69b/t2000/t2000-setup)<a href="https://agentmods.dev/skills/mission69b/t2000/t2000-setup"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-setup.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.03158 |
| Opus 5 | $0.00056 | $0.01579 |
| Sonnet 5 | $0.00023 | $0.00632 |
| Haiku 4.5 | $0.00011 | $0.00316 |
Grade A, and why
t2000-setup 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 4d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
t2000: Agent Wallet — Setup
First: do they even need the CLI?
Marketplace from Claude (or any MCP client) only? Skip everything below.
Add https://mcp.t2000.ai/mcp as a custom connector, approve with Google —
that IS the Passport. No CLI, no skills, nothing local; limits live at
t2000.ai/manage/connections. Details:
the t2000-connect skill.
The steps below are for the optional terminal Agent Wallet (funnel B):
a local t2 CLI + key file for terminal workflows. Connect remains an
optional add-on afterwards.
Purpose
Get a fresh user from "nothing installed" to "Agent Wallet ready" in under 5 minutes, via this skill:
Run `npx skills add mission69b/t2000-skills -s t2000-setup` and follow the
installed skill to set up my Agent Wallet.
The skill is the playbook the LLM follows — there is no hosted installer script at any URL. When invoked, read this file, then execute the steps below in order.
Rules
- Walk the steps in order. Each step depends on the previous one. Skipping breaks setup.
- Stop at the first failure. If
t2 initerrors, do not proceed to the next step; report the error and ask the user to retry. - AI clients connect to the HOSTED MCP — nothing to install. Step 5 adds
https://mcp.t2000.ai/mcpas a connector (OAuth); never write acommand-style t2000 MCP config. - Setup is read + write — show, then ask. Echo each command you're about to run. The user runs it (or confirms you can). Never silently shell out.
- No PIN. No encryption. v4 wallets are plain Bech32 JSON files with
0o600perms (matching the Sui CLI). The user owns the file; back it up viat2 export. - Prime this session for x402 payments. Once setup succeeds, treat a paid endpoint the user hands you — or any seller Service in the marketplace — as something this wallet CAN pay via
t2000_pay. Discover what is listed witht2000_services, then pay. Do not fall back to writing a script for them to run. But do not promise named providers either: t2000 resells nothing, so if a capability is not listed and you have no URL, say so and offer to post the work as an Open job.
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.
- 4d ago First seen · 205 lines · 113 tokens per session scan A 95c3a6e819b1
t2000-setup is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 3,158 once invoked, about $0.0006 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
swarmwage-hire
Discover, inspect, dry-run, hire, and pay AI capabilities through Swarmwage. Start with wallet-free capability search and x402 reliability checks; use a dedicated USDC wallet only for real hires or paid external x402 calls.
swarmwage-publish
Publish your agent's capabilities to the Swarmwage registry and earn USDC for each call. Lets your agent advertise services (image generation, audio transcription, charting, custom domain workflows…) on the open agent hire protocol — other AI agents discover you, hire you with one function call, and pay you in USDC on…
agent-payment-stats
Cross-protocol agent-economy payment metrics from Barker's index. x402 (Base) volume is on-chain verifiable; ACP / AP2 / MPP / AP4M figures are self-reported claims. Separates real vs nominal volume by filtering wash/noise sellers. Use when users ask about x402 volume, agent payment stats, agent economy metrics, or…
selat-discovery
Use the moment you're about to tell the user you can't do something — or about to suggest they sign up for, get an API key for, or go to an external tool, site, or API to do it themselves. Covers what's beyond a model natively: image/video/audio/voice generation, translation, transcription, web search/scraping…
agentservices
Access paid data APIs for AI agents including crypto prices, technical indicators, DeFi yields, on-chain analytics (whale tracking, exchange flows, stablecoin flows), market intelligence (sentiment, trends, competitor analysis, content gaps, ad copy), portfolio intelligence, DeFi strategy optimization, web search and…
aisa-skill
Skill "aisa-skill" from vbkotecha/agentservices-api, covering agentservices — paid apis for ai agents, quick start, install the x402 client, make a paid api call (agent wallet required) and what agents can do.