aotrust-notarize

aotrust-notarize is a skill for Claude Code, Codex from GitSerge-crypto/aotrust-skills. It costs 134 tokens per session (5,874 once invoked), scanned A, original, MIT.

A tool for creating a public cryptographic receipt that proves a digital file or message existed at a particular time. It records the artifact’s hash, not the artifact itself, and charges $0.01 in USDC.

In plain words
What is it for?
Use it to notarize emails, documents, contracts, source code, or other digital artifacts when you need proof of existence at a specific time.
Why use it?
It provides independently checkable evidence of when something existed without uploading the original. Payment and publication are irreversible, so each notarization requires the user’s approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to notarize emails, documents, contracts, source code, or other digital artifacts when you need proof of existence at a specific time.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gitserge-crypto/aotrust-skills/aotrust-notarize
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 GitSerge-crypto/aotrust-skills --skill aotrust-notarize
Clone the repo
git clone --depth 1 https://github.com/GitSerge-crypto/aotrust-skills

Made for: Claude Code, Codex.

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 aotrust-notarize

README.md
[![agentmods](https://agentmods.dev/badge/skills/gitserge-crypto/aotrust-skills/aotrust-notarize/github.svg)](https://agentmods.dev/skills/gitserge-crypto/aotrust-skills/aotrust-notarize)
Your own site
<a href="https://agentmods.dev/skills/gitserge-crypto/aotrust-skills/aotrust-notarize"><img src="https://agentmods.dev/badge/skills/gitserge-crypto/aotrust-skills/aotrust-notarize/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.

agentmods 80×15 button for aotrust-notarize

Your own site · 80×15
<a href="https://agentmods.dev/skills/gitserge-crypto/aotrust-skills/aotrust-notarize"><img src="https://agentmods.dev/badge/skills/gitserge-crypto/aotrust-skills/aotrust-notarize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,874 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00134 $0.05874
Opus 5.5 $0.00054 $0.02350
Sonnet 5.5 $0.00027 $0.01175
Haiku 4.5 $0.00013 $0.00587

Measured today against content hash b2b4ab110716, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aotrust-notarize scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://api.aotrust.link/notarize \
aotrust-notarize/SKILL.md · 429 lines

How it starts

The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AOTrust — Cryptographic Proof of Existence

This skill interacts with an external paid API. Read this before invoking.

What leaves your machine Where it goes Reversible?
work_hash (SHA-256 of your artifact) api.aotrust.link No — hash is public in the PDR
agent_sig + agent_pubkey (optional, bilateral) api.aotrust.link No — stored in notary ledger
EIP-3009 payment signature Base Mainnet (on-chain) No — $0.01 USDC, irreversible

Rules:

  • Confirm with the user before notarizing. Show the artifact hash and ask: "Notarize this for $0.01 USDC?"
  • Never use an unattended wallet. Payment requires manual approval for every transaction.
  • Do not let the agent manage private keys. The user signs EIP-3009 manually or via a wallet that requires confirmation.
  • The artifact itself is never uploaded — only its hash. But the hash is public in the PDR and on NEAR blockchain.

A PDR (Provenance Data Record) is a 239-byte cryptographic receipt proving that a digital artifact existed at a specific point in time.

Works with any digital artifact: emails, documents, contracts, source code, AI outputs, research notes, datasets, photos, logs, sensor readings.

The artifact itself is never uploaded — only its SHA-256 hash.

Receipts are anchored hourly to NEAR blockchain (cumulative Merkle log, RFC 9162 inclusion/consistency proofs). $0.01 per proof. No account needed.

Two Ways to Connect

Interface Best for How
MCP (recommended for AI agents) AI agents with MCP support tools/list → notary_notarize_paid (x402 in-band micropayment)
HTTP API (for developers) Direct integration, scripts, CI/CD POST /notarize → 402 → pay → 200

Both interfaces produce the same PDR. Pick one.


Interface 1: MCP (for AI Agents)

Endpoint

https://api.aotrust.link/mcp

Read the full file on GitHub · 429 lines

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. today Changed · +1 lines b2b4ab110716
  2. 2d ago Changed · +50 lines · +29 tokens per session 9322eb9cb52c
  3. 18d ago Changed · +3 lines 98a7414218b5
  4. 1mo ago Changed · +6 lines · +6 tokens per session ee206aa5fe55
  5. 1mo ago Changed d32be4c231fd
  6. 1mo ago Changed · +8 lines a316f1e0ba27
  7. 1mo ago First seen · 361 lines · 99 tokens per session scan A d5c49463ac5f

Subscribe to this mod's changes

aotrust-notarize is a skill published in the GitHub repository GitSerge-crypto/aotrust-skills (1 stars, last pushed yesterday), licensed MIT. It adds 134 tokens to every session and 5,874 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

witnessd

Create tamper-evident, third-party evidence of exactly what a public URL or API endpoint returned at a specific moment, using witnessd (a neutral witness service; $0.02 per snapshot paid via x402 in USDC on Base; hourly Merkle anchoring on-chain; certificates anyone can verify). Use when about to pay or transact with…

jschunter/witnessd-mcp · 187 tokens

genpark-ghostwriter

Transforms business intent into legally-binding smart contract drafts and delivers them via GenPark API.

alphaparkinc/openclaw-genpark-ghostwriter · 23 tokens

genpark-ghostwriter

Transforms business intent into legally-binding smart contract drafts and delivers them via GenPark API.

alphaparkinc/genpark-ucp · 0 tokens

genpark-ghostwriter

Transforms business intent into legally-binding smart contract drafts and delivers them via GenPark API.

alphaparkinc/genpark-ghostwriter · 23 tokens

category-designer

Define a new category where your product wins by default. Reframe the buying decision. Triggers on: "create a category", "category design", "define my category", "category of one", "reframe the market", "position as category king", "new category", "category creation", "own a category", "category strategy"…

Affitor/affiliate-skills · 103 tokens

surf

Surf (asksurf.ai) is RETIRED on BlockRun and the blockrunsurf tool was REMOVED in 0.49.0 — the gateway has answered every /v1/surf/ path with HTTP 410 endpointretired since 2026-09-06. Use this skill to route a former Surf question (on-chain SQL, wallet labels and net worth, CEX order books, social mindshare, news) to…

BlockRunAI/blockrun-mcp · 110 tokens