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 0xddneto/AI-Proof-of-Us --skill aipou-farminggit clone --depth 1 https://github.com/0xddneto/AI-Proof-of-UsWrote 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/0xddneto/ai-proof-of-us/aipou-farming)<a href="https://agentmods.dev/skills/0xddneto/ai-proof-of-us/aipou-farming"><img src="https://agentmods.dev/badge/skills/0xddneto/ai-proof-of-us/aipou-farming/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/0xddneto/ai-proof-of-us/aipou-farming"><img src="https://agentmods.dev/badge/skills/0xddneto/ai-proof-of-us/aipou-farming.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00070 | $0.00794 |
| Opus 5 | $0.00035 | $0.00397 |
| Sonnet 5 | $0.00014 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
aipou-farming 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 12d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIPOU Farming
Use the aipou MCP tools to turn completed AI work into signed receipts. Keep private keys, raw prompts, model outputs, and private file contents out of tool arguments and responses.
AIPOU is for humans working with AI agents: coding, debugging, researching, reviewing, writing, and coordinating meaningful work. It records private receipts first. Token claims are optional, validator-approved, and only run after an explicit user request.
Read references/protocol.md before the first operation in a session.
Direct MCP Tool Calls
The AIPOU operations below are native tools in the current agent session. Call them directly by tool name.
- Do not translate an AIPOU tool call into a shell command, CLI command,
npxcommand, HTTP request, or code snippet. - Never invent commands such as
aipou begin,aipou complete, oraipou claim. - Use only tool results returned by the MCP server. Never fabricate a nonce, receipt ID, reward, signature, or settlement result.
- If an expected AIPOU tool is not present in the current tool list, stop and report that the MCP integration is unavailable in that session.
Record Work
- Call
get_aipou_identityand confirm that a dedicated farming wallet is configured. - Before meaningful work, hash a short non-sensitive task description with Keccak-256.
- Call
begin_ai_taskwith the real provider, model, task hash, and client name. - Preserve the returned nonce only for this task.
- Complete the requested work.
- Hash the final result or a stable non-sensitive summary with Keccak-256.
- Call
complete_ai_taskwith the nonce, honest token counts when available, elapsed seconds, and output hash. - Report the receipt ID, trust tier, estimated reward, and settlement status.
Never invent provider evidence. Omit it unless the provider supplied a verifiable signature from a configured key.
Claim Rewards
After a broad explicit user request such as claim my AIPOU, call settle_all_ai_rewards so every currently eligible pending receipt in the shared AIPOU data directory is processed in bounded batches. Use settle_ai_rewards only when the user asks for one limited batch. Settlement submits onchain transactions; your host's own transaction confirmation policy still applies and must never be bypassed. Report any receipts the validator skipped by policy, with their reasons.
What ships with it
3 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.
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.
- 12d ago First seen · 57 lines · 70 tokens per session scan A 23f295121e7e
aipou-farming is a skill published in the GitHub repository 0xddneto/AI-Proof-of-Us (4 stars, last pushed 6d ago), licensed MIT. It adds 70 tokens to every session and 794 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
scvd-general-store
A live x402 practice counter: real settlement, no sandbox, from $0.001. Free conformance checking for any issuer's signed offers and receipts, ours or a competitor's. An evidence observatory: signed observation of what other endpoints and payments actually did, never a ranking. Reachable six ways, including browser…
x402-before-you-pay
Before an agent pays an x402 endpoint, read its 402 terms and run scvd.store's free preflight and dry run over the same bytes; decide pay / donotpay / cannottell with every reason named. Use when code or an agent is about to call a paid x402 URL, when a 402 looks wrong, or when a payment "never went through".…
scvd-general-store
A live x402 practice counter: real settlement, no sandbox, from $0.001. Free conformance checking for any issuer's signed offers and receipts, ours or a competitor's. An evidence observatory: signed observation of what other endpoints and payments actually did, never a ranking. Reachable six ways, including browser…
aomi-transact
Build natural-language crypto/DeFi agents and EVM MCP plugins (Claude Code, Cursor, Codex, Gemini). Aomi turns prompts into wallet-signed txs on Ethereum, Base, Arbitrum, Optimism, Polygon, Linea — non-custodial, fork-simulated. 40+ apps: Uniswap, Aave, Lido, Morpho, GMX, Hyperliquid, Polymarket.
aomi-transact-v2
Use this skill to operate the Aomi CLI for natural-language crypto and DeFi workflows, including balance checks, route simulation, transaction review, and explicit user-approved signing flows across EVM chains.
CTRL
Build on-chain automation on Base via CTRL - DCA, price-gated swaps, launchpad sniping, or whale-follow that run autonomously after one EIP-5792 wallet signature, bounded by preset caps.