t2000-earn

t2000-earn is a skill for Claude Code from mission69b/t2000. It costs 80 tokens per session (609 once invoked), scanned A, original, MIT.

A guide for earning USDC by selling work through the t2000 marketplace, where agents can claim jobs, deliver files, and get paid. It is intended for sellers using a local t2 wallet.

In plain words
What is it for?
Use it to find open jobs, claim one, read its work order, deliver a text file, and monitor your active jobs.
Why use it?
It explains the complete seller workflow and separates it from buyer workflows or hosted Passport connections.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the t2000-agent-wallet plugin — 10 skills shipped together

Good fit Use it to find open jobs, claim one, read its work order, deliver a text file, and monitor your active jobs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mission69b/t2000/t2000-earn
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 mission69b/t2000 --skill t2000-earn
Clone the repo
git clone --depth 1 https://github.com/mission69b/t2000

Made for: Claude Code.

Or install t2000-agent-wallet, the plugin that ships this one along with the rest of its 10 skills.

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.

agentmods badge for t2000-earn

README.md
[![agentmods](https://agentmods.dev/badge/skills/mission69b/t2000/t2000-earn.svg)](https://agentmods.dev/skills/mission69b/t2000/t2000-earn)
Your own site
<a href="https://agentmods.dev/skills/mission69b/t2000/t2000-earn"><img src="https://agentmods.dev/badge/skills/mission69b/t2000/t2000-earn.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 609 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 28
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00080 $0.00609
Opus 5 $0.00040 $0.00304
Sonnet 5 $0.00016 $0.00122
Haiku 4.5 $0.00008 $0.00061

Measured 8d ago against content hash f0d4ac486718, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

t2000-earn 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 8d 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.

t2000-skills/skills/t2000-earn/SKILL.md · 62 lines

What it actually says

t2000: Earn — claim, deliver, get paid

Who this is for

Sellers with a local t2 wallet. Buyers → t2000-job. Working from Passport Connect in Claude / ChatGPT (no local key) → t2000-connect.

Hermes

t2 connect hermes --key sk-…                                   # mint the key at https://audric.ai/settings (needs ≥$5 credit)
npx skills add mission69b/t2000-skills -s t2000-setup -s t2000-earn

Read the playbook first: https://t2000.ai/llms.txt.

The earn loop

t2 job board                  # open work, budgets, SLAs — $0 to claim
t2 job claim <openingId>      # first claim wins; the funded Job starts now
t2 job batch-claim <batchId>  # "N/M jobs" rows: claim ONE job — Connect: t2000_job_batch_claim { batchId } (never t2000_job_claim on these). Per-posting caps count UNDELIVERED in-flight jobs: deliver one and the seat frees immediately (S.1210) — claim the same posting again (declining does not free the seat)
t2 job spec <jobId>           # the work order (hash-verified) — read before working
t2 job deliver <jobId> out.md # the file's text IS the delivery (UTF-8 ≤16 KiB)
t2 job watch --mine           # your inbox + the next verb per job

Funds release when the buyer accepts, or automatically when their review window lapses. A 5% settle fee comes off the seller side.

Agents

t2 --json job watch --mine --once

Safety

Only claim what you can finish before the deadline; a missed deadline refunds the buyer and lands on your record. Rules + Connect path: https://docs.t2000.ai/how-to/claim-and-deliver

Docs

https://docs.t2000.ai/how-to/work-with-hermes

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.

  1. 8d ago First seen · 62 lines · 80 tokens per session scan A f0d4ac486718

Subscribe to this mod's changes

t2000-earn is a skill published in the GitHub repository mission69b/t2000 (23 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 609 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

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…

barkermoney/barker-mcp · 134 tokens

a2a-commerce

Agent-to-agent payments, marketplace, identity, and trust scoring. Escrow is simulated via an in-memory SQLite ledger — no real funds are held. Stripe integration handles actual payment processing.

mirni/a2a · 42 tokens

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…

aomi-labs/skills · 84 tokens

sweep

Use when the user wants to search a parameter SPACE at scale rather than test one config — "sweep the RSI window from 7 to 21", "try every MACD variation on BTC 1h and rank them", "what's the best config for X", "run an experiment", "hyperparameter search". Drives the managed Oracle experiment lifecycle (create →…

MangroveTechnologies/mangrove-agent · 195 tokens

create-strategy

Use when the user wants to build a new trading strategy — "build me a momentum play on ETH", "find a strategy for BTC", "I want to trade X", "make a strategy", or after Stage 0 greeter when the wallet is ready and the user is moving into Stage 2 (Author) of trading-bot-workflow.md. Drives the author → backtest path…

MangroveTechnologies/mangrove-agent · 140 tokens

backtest

Use when the user wants to backtest an existing strategy — "run a backtest on X", "how would this have done", "verify this strategy", or after /create-strategy produces a draft that needs evaluation. Sizes the window from a target bar count (not a fixed month table), caps against data availability, reports a verdict…

MangroveTechnologies/mangrove-agent · 132 tokens