alpha-scanner

alpha-scanner is a skill for Claude Code, Codex from Clawpump/agents-skills. It costs 0 tokens per session (403 once invoked), scanned A, original, MIT.

A skill that scans Solana, a blockchain network, for early token-trading signals and presents the findings as structured reports.

In plain words
What is it for?
Looking for newly launched tokens, volume spikes, social catalysts, and simultaneous buying by wallets with profitable trading histories.
Why use it?
It organizes information about new tokens, unusual trading activity, social attention, and experienced wallets in one report.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/clawpump/agents-skills/alpha-scanner
Any agent
npx skills add Clawpump/agents-skills --skill alpha-scanner
Clone the repo
git clone --depth 1 https://github.com/Clawpump/agents-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 alpha-scanner

README.md
[![agentmods](https://agentmods.dev/badge/skills/clawpump/agents-skills/alpha-scanner.svg)](https://agentmods.dev/skills/clawpump/agents-skills/alpha-scanner)
Your own site
<a href="https://agentmods.dev/skills/clawpump/agents-skills/alpha-scanner"><img src="https://agentmods.dev/badge/skills/clawpump/agents-skills/alpha-scanner.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00403
Opus 5 $0.00000 $0.00201
Sonnet 5 $0.00000 $0.00081
Haiku 4.5 $0.00000 $0.00040

Measured 5d ago against content hash 44564f44628e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

alpha-scanner 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 5d 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/alpha-scanner/SKILL.md · 60 lines

What it actually says

Alpha Scanner

You actively scan for early trading opportunities on Solana and present them as structured alpha reports.

What to Scan For

New Token Launches

  • Tokens launched in the last 1-6 hours on pump.fun or Raydium
  • Filter: minimum $5k liquidity, at least 50 unique holders
  • Highlight tokens with rapid organic holder growth

Unusual Volume

  • Tokens with volume spike >5x their 7-day average
  • Focus on tokens between $100k-$10M market cap (sweet spot for early alpha)
  • Ignore volume from wash trading patterns (same wallets cycling)

Social Catalysts

  • Tokens being mentioned by accounts with >10k followers
  • Trending on crypto Twitter/X in the last 2 hours
  • New partnerships or integrations announced

Smart Money

  • Wallets known for consistent profitable trades entering new positions
  • Multiple profitable wallets accumulating the same token simultaneously

Alpha Report Format

ALPHA ALERT: [TOKEN] ([symbol])
Time: [timestamp]
Signal: [what triggered this alert]

Market Cap: [mcap]
Liquidity: [amount]
Volume 24h: [amount] ([X]x avg)
Holders: [count] ([+X] in last hour)

Why it's interesting:
- [bullet points]

Risk Factors:
- [bullet points]

Confidence: [Low/Medium/High]

Filtering Rules

  • Never surface tokens with mint authority still enabled
  • Skip tokens where top wallet holds >50% of supply
  • Skip tokens with less than $5k in liquidity
  • Skip tokens that are obvious copies/forks of existing tokens without innovation
  • Maximum 5 alpha alerts per hour to avoid noise

Rules

  • Always include risk factors — no pure hype
  • Clearly label confidence level
  • Never frame alerts as buy recommendations
  • Prioritize quality over quantity
  • Include enough data for the user to do their own research
Files

What ships with it

1 file 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.

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. 5d ago First seen · 60 lines · 0 tokens per session scan A 44564f44628e

Subscribe to this mod's changes

alpha-scanner is a skill published in the GitHub repository Clawpump/agents-skills (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 403 tokens. 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.