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/augstentatious/proofpay-agent/proofpaynpx skills add augstentatious/proofpay-agent --skill proofpaygit clone --depth 1 https://github.com/augstentatious/proofpay-agentWhat 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 | $0.00014 | $0.00259 |
| Opus 5 | $0.00007 | $0.00130 |
| Sonnet 5 | $0.00003 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
proofpay 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 yesterday.
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.
What it actually says
ProofPay
Use ProofPay only for an artifact already present in the operator-owned artifact root.
Flow
- Call
proofpay__create_invoicewithartifact_name, decimalamount, and an optional buyer label. - Return the generated Solana Pay URI and invoice ID to the buyer.
- Call
proofpay__invoice_statusto poll finalized chain state. - Call
proofpay__release_artifactonly after status ispaid. - Return the released file path to the operator/channel delivery layer.
Boundaries
- Recipient, mint, amount ceiling, roots, RPC, and decimals are operator config, not model arguments.
- Never request, expose, log, or transmit wallet private keys.
- Never claim payment before
invoice_statusreturnspaid. - A failed integrity check is terminal for that artifact until an operator restores it.
- Do not release plaintext for
pendingorexpiredinvoices.
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.
- yesterday First seen · 34 lines · 14 tokens per session scan A 331ed9241b5c
proofpay is a skill published in the GitHub repository augstentatious/proofpay-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 259 once invoked, about $0.0001 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
model-context
MCP (Model Context Protocol) - Build AI-native servers with tools, resources, and prompts. TypeScript/Python SDKs for Claude Desktop integration.
research-blip-2
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of...
mdc-langchain-js
This guide provides opinionated, actionable best practices for building robust and maintainable LLM applications with langchain-js, emphasizing modularity, type safety, observability, and testing.
research-compiler
Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, c...
research-knowledge-distillation
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-sour...
mdc-langchain
Definitive guidelines for writing maintainable, performant, and robust LangChain applications using modern best practices (LCEL, LangGraph, Pydantic, createagent).