Submit Hook logo

Submit Hook

Organization
aeonfun
submit-hook

Submit a deployed Uniswap v4 hook to the public univ4-hooks registry - format the listing, open a PR (issue fallback) so it lists on the hook marketplace.

Overview

Publisheraeonfun
Repositoryaeon
Skill namesubmit-hook
Stars
771
Forks
280
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aeonfun on GitHub. Read the source before you install it.

Installation

Install the Submit Hook AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/aeonfun/aeon/tree/main/skills/submit-hook
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aeonfun/aeon.git /tmp/aeon
mkdir -p .claude/skills
cp -r /tmp/aeon/skills/submit-hook .claude/skills/submit-hook
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Submit Hook in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Submit Hook on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Submit Hook is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

${var} - a hook address (0x...) to submit. Empty means the most recent live mainnet deploy in memory/state/hook-deploys.json.

Today is ${today}. This skill takes a hook this instance already deployed and lists it on the public registry aeonfun/univ4-hooks (the source behind the aeon hook marketplace). It does the formatting the registry expects, then opens a PR. The flags and callbacks are decoded from the address by the registry, so this skill only supplies the address, the chain, and the human-readable listing.

The mechanics (clone, write the entry, regenerate the registry, open the PR, fall back to an issue when there is no push access) live in skills/submit-hook/submit-univ4.py, so all GitHub egress stays inside that helper.

What lists, and what does not

  • Only live mainnet deploys. A dry-run or a testnet deploy is never submitted (the registry lists real, verifiable hooks). Skip with SUBMIT_HOOK_SKIP.
  • Only registry-supported chains. The registry's chains.json covers ethereum base robinhood monad bnb arbitrum unichain. A deploy on any other chain is skipped (SUBMIT_HOOK_UNSUPPORTED_CHAIN); note it and stop.
  • Idempotent. The helper skips if the address (any chain) or the slug is already listed, so re-running is safe.

Steps

  1. Pick the deploy. Read memory/state/hook-deploys.json (a list of deploy records). If ${var} is a 0x... address, select the record whose hookAddress matches it; else select the most recent record with network: "mainnet". No matching record means notify and exit SUBMIT_HOOK_NONE.

  2. Gate it. If the record's network is not mainnet, exit SUBMIT_HOOK_SKIP. If its chain is not one of ethereum base robinhood monad bnb arbitrum unichain, exit SUBMIT_HOOK_UNSUPPORTED_CHAIN (the registry cannot list it yet). Confirm int(hookAddress,16) & 0x3FFF == int(flags,16); if not, the record is inconsistent, so notify and exit SUBMIT_HOOK_BAD_RECORD.

  3. Name it. Derive a PascalCase contract-style name from the record's brief/feature (a market-hours gate becomes MarketHoursGate). This is the marketplace title and the hooks/<slug>.json filename.

  4. Classify it. From the brief and flagNames, choose:

    • category: one of Fees Rewards Access Games Orders Launch. A gate/allowlist is Access; a fee/volatility hook is Fees; a tribute/buyback/leaderboard is Rewards; a block/price/volume game is Games; limit/async/MEV ordering is Orders; launch/anti-bot/anti-rug is Launch.
    • klass: VALUE if the hook returns a delta or moves tokens (a *ReturnDelta flag), FEE if it sets a dynamic LP fee, else GATE.
    • template: map the record's template. dynamic stays dynamic, noop stays noop, anything else (freeform/skim) becomes freeform.
  5. Write the listing prose from the brief:

    • mechanic: one punchy line for the tile.
    • plain: 2-4 plain-language sentences a non-dev follows, for the modal.
    • rules: the exact rules the hook enforces, one per line (2-4).
  6. Submit. Run the helper (a live mainnet deploy that cleared this instance's deploy gates lists as an aeon, verified hook):

    bash
    python3 skills/submit-hook/submit-univ4.py \
      --address "$HOOK_ADDRESS" --chain "$CHAIN" \
      --name "$NAME" --category "$CATEGORY" --klass "$KLASS" \
      --template "$TEMPLATE" --stage deployed --source aeon --verified \
      --date "$(echo "$TIMESTAMP" | cut -c1-10)" \
      --mechanic "$MECHANIC" --plain "$PLAIN" \
      --rule "$RULE1" --rule "$RULE2" [--rule "$RULE3"]

    Add --dry-run first to print the entry and the intended action without touching the registry, then drop it to actually open the PR. The helper prints the PR URL (or the issue URL on a fallback, or already listed).

  7. Notify + exit. Send a short note (hook name, chain, PR/issue URL). Exit SUBMIT_HOOK_OK (PR/issue opened or already listed).

Degrade rules

  • No ledger or no matching record: SUBMIT_HOOK_NONE (notify, never fail hard).
  • Testnet or dry-run deploy: SUBMIT_HOOK_SKIP.
  • Chain not in the registry: SUBMIT_HOOK_UNSUPPORTED_CHAIN.
  • flags != address & 0x3FFF in the record: SUBMIT_HOOK_BAD_RECORD.
  • No push access to the registry: the helper files the structured submission issue instead and still exits SUBMIT_HOOK_OK.

Notes

  • The registry validates every PR: flags/callbacks are recomputed from the address, the schema is enforced, and the aggregated hooklist.json is checked. The helper regenerates hooklist.json + HOOKS.md before pushing so that check passes.
  • deploy-uni-hook calls this same helper on a successful live deploy, so a hook usually lists itself the moment it lands. Run this skill by hand to resubmit an older deploy or one that failed to auto-list.
  • The helper never puts a token on a command line. It uses the gh CLI, which reads GH_TOKEN from the environment.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Submit Hook AI skill do?

Submit a deployed Uniswap v4 hook to the public univ4-hooks registry - format the listing, open a PR (issue fallback) so it lists on the hook marketplace.

Why use Submit Hook on TypingMind?

Because you install it once and use it with any model. Submit Hook is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Submit Hook in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aeonfun/aeon/tree/main/skills/submit-hook. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Submit Hook?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Submit Hook?

As many as you like. As long as a model supports skills, you can use Submit Hook with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Submit Hook AI skill free?

Yes. It is published on GitHub by aeonfun under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇