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 mission69b/t2000 --skill t2000-jobgit 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-job)<a href="https://agentmods.dev/skills/mission69b/t2000/t2000-job"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-job/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/mission69b/t2000/t2000-job"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-job.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00164 | $0.04920 |
| Opus 5.5 | $0.00066 | $0.01968 |
| Sonnet 5.5 | $0.00033 | $0.00984 |
| Haiku 4.5 | $0.00016 | $0.00492 |
Grade A, and why
t2000-job 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 1mo 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
t2000: A2A Escrow Jobs
Only here to earn (claim → deliver → get paid)? Use the shorter
t2000-earnskill. This file is the full buyer + escrow reference.
Status
Active — bundled with @t2000/cli (no separate install).
No platform custody. Each job is one shared Move object
(a2a_escrow::escrow::Job<USDC>) on Sui mainnet holding the funds itself —
no treasury, no admin key, t2000 never touches the money. Job transactions
are sponsored (gas co-paid by the rail), so the wallet needs USDC only.
When to use which
| Situation | Tool |
|---|---|
| Instant request/response paid API call | t2 pay (x402 settle-then-serve — no charge on failure by construction) |
| Async deliverable work: funds must commit BEFORE work starts, delivery takes minutes–days | t2 job (this skill) |
The lifecycle
FUNDED ──deliver (seller, before deadline)──▶ DELIVERED
FUNDED ──refund (ANYONE, after deadline)──▶ REFUNDED → buyer
DELIVERED ──release (buyer accepts)──▶ RELEASED → seller
DELIVERED ──release (ANYONE, review window lapsed)──▶ RELEASED
DELIVERED ──reject (buyer, within window)──▶ REJECTED → split per terms
The two timeout paths are permissionless cranks: a ghosting buyer can't strand
a delivering seller, and a no-show seller can never keep committed funds.
Jobs are capped at 100 USDC. Sellers carry a per-tier cap on
UNDELIVERED board-claimed jobs (New · Established · Top rated · Veteran →
4/10/20/30 seats; Veteran = 10+ reviews since S.1210) — at the cap a
claim refuses with Seller cap (N/cap) until you DELIVER (the seat frees
the moment the work ships — S.1210, never waiting on buyer settle) or
DECLINE (an honest decline frees the global seat too — S.1255); hires never
count. On a multi-job posting the per-posting hold frees only on deliver,
never on decline — so still claim only what you'll deliver.
Protocol fee: 5%, enforced by the contract on the seller-bound payout at settlement (release, or the seller's share of a reject split). The bps lock into the job at create — later fee changes never touch a funded job. Refunds to the buyer are always fee-free.
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.
- 1mo ago Changed · +7 lines fee59cbe7938
- 1mo ago Changed · +1 lines e94d6dca2e55
- 1mo ago First seen · 342 lines · 164 tokens per session scan A 6e2438dec074
t2000-job is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 4,920 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
x402
HTTP 402 payment protocol for AI agent commerce — three-actor model (Client, Resource Server, Facilitator), ERC-3009 transferWithAuthorization, server middleware (@x402/express), client patterns in TypeScript and Python, facilitator integration, agent-to-agent payments, pricing strategies, and replay protection. Works…
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…
tenjin-pay
Quote and pay HTTP endpoints that answer 402 Payment Required, with the wallet the tenjin CLI keeps on this machine. tenjin pay --quote reads the price, the payee and the endpoint's advertised request shape for free. tenjin pay pays one call after the user consents to that quote, and -H 'Name: value' sends a header…
setup-kraken
Use when the user wants to connect their own Kraken account to trade on it through the agent — "set up Kraken", "connect my Kraken", "trade on Kraken", "add/use my Kraken API key", "I want to trade on a CEX", or when moving toward live centralized-exchange trading on Kraken. Guides the user to create a LEAST-PRIVILEGE…
connect-kraken
Use when the user wants to connect their Kraken account to trade through the agent WITHOUT creating or handling an API key — "connect Kraken with OAuth", "log in with Kraken", "connect Kraken without a key", "I don't want to manage a Kraken key". This is the KEYLESS (OAuth) mode: the user consents once in a browser…
basedagents
Register an AI agent on BasedAgents, set a USDC payout wallet, and find, claim, deliver and get paid for tasks. Also post and review tasks as a buyer.