clawd-phoenix-mm

clawd-phoenix-mm is a skill for Claude Code, Codex from x402agent/solana-clawd. It costs 46 tokens per session (1,097 once invoked), scanned A, original, MIT.

An on-chain market-making guide for Phoenix, a Solana central limit order book. Its Rust program places buy and sell limit orders around a reference price and refreshes them regularly.

In plain words
What is it for?
Use it to check or build the market-maker program, preview its run command, and configure quotes for a selected market and ticker.
Why use it?
It gives a structured way to maintain two-sided quotes and seek maker rebates while controlling quote distance, size, and refresh timing.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to check or build the market-maker program, preview its run command, and configure quotes for a selected market and ticker.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/x402agent/solana-clawd/clawd-phoenix-mm
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 x402agent/solana-clawd --skill clawd-phoenix-mm
Clone the repo
git clone --depth 1 https://github.com/x402agent/solana-clawd

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 clawd-phoenix-mm

README.md
[![agentmods](https://agentmods.dev/badge/skills/x402agent/solana-clawd/clawd-phoenix-mm/github.svg)](https://agentmods.dev/skills/x402agent/solana-clawd/clawd-phoenix-mm)
Your own site
<a href="https://agentmods.dev/skills/x402agent/solana-clawd/clawd-phoenix-mm"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/clawd-phoenix-mm/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 clawd-phoenix-mm

Your own site · 80×15
<a href="https://agentmods.dev/skills/x402agent/solana-clawd/clawd-phoenix-mm"><img src="https://agentmods.dev/badge/skills/x402agent/solana-clawd/clawd-phoenix-mm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,097 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.
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 $0.00046 $0.01097
Opus 5 $0.00023 $0.00549
Sonnet 5 $0.00009 $0.00219
Haiku 4.5 $0.00005 $0.00110

Measured 9d ago against content hash 74796fc2f8df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

clawd-phoenix-mm 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 9d 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.

skills/clawd-phoenix-mm/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

clawd-phoenix-mm

Use this skill when the user wants to:

  • Run the Phoenix on-chain market-maker (mm Rust binary)
  • Check mm workspace / build the mm binary
  • Configure quote edge, quote size, refresh frequency, or price-improvement behavior
  • Earn maker rebates by placing resting orders on the Phoenix CLOB

What the On-Chain Market-Maker Does

The mm binary (from perps/phoenix-onchain-market-maker-master) is a Rust program that:

  1. Reads the current Coinbase ticker price for a symbol (e.g., SOL-USD)
  2. Places a two-sided quote (bid + ask) around the mid price with a configurable edge
  3. Refreshes the quote every N milliseconds
  4. Collects maker rebates when orders fill

The maker earns fees instead of paying them — the wider the edge, the more rebate per fill.

Workspace Setup

# Check mm workspace status
clawd perps onchain-mm status

# Build the mm binary (Rust / cargo)
clawd perps onchain-mm build

# Preview the exact cargo run command
clawd perps onchain-mm plan \
  --market <PHOENIX_MARKET_PUBKEY> \
  --ticker SOL-USD \
  --quote-edge-bps 3

Environment variables:

  • CLAWD_ONCHAIN_MM_ROOT — path to perps/phoenix-onchain-market-maker-master
  • CLAWD_ONCHAIN_MM_MARKET — Phoenix market pubkey (required for live run)
  • CLAWD_ONCHAIN_MM_TICKER — Coinbase ticker (default: SOL-USD)
  • CLAWD_ONCHAIN_MM_RPC_URL — Solana RPC endpoint

Running the Market-Maker

The run is gated — all three must be set:

CLAWD_ONCHAIN_MM_LIVE=true OPERATOR_CONFIRMED=true \
  clawd perps onchain-mm run \
  --market <PUBKEY> \
  --ticker SOL-USD \
  --quote-edge-bps 3 \
  --quote-size 100000000 \
  --yes

Key parameters:

Flag Default Description
--quote-edge-bps 3 Half-spread in bps (edge around mid)
--quote-size 100000000 Quote size in quote atoms
--refresh-ms 2000 Quote refresh interval ms
--price-improvement ignore join / dime / ignore
--post-only true Reject if would cross the book

Read the full file on GitHub · 123 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. 9d ago First seen · 123 lines · 46 tokens per session scan A 74796fc2f8df

Subscribe to this mod's changes

clawd-phoenix-mm is a skill published in the GitHub repository x402agent/solana-clawd (24 stars, last pushed 3mo ago), licensed MIT. It adds 46 tokens to every session and 1,097 once invoked, about $0.0002 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 2026-09-03.