alph-bot-strategy

alph-bot-strategy is a skill for Claude Code, Codex from Outsharp/shipp-skills. It costs 0 tokens per session (2,773 once invoked), scanned A, original, Apache-2.0.

A writing guide for creating STRATEGY.md files for Alph trading bots. These files describe how a bot should reason about markets, such as prediction markets or sports events.

In plain words
What is it for?
Use it to document a trading approach, define its market and risk categories, and prepare it for use with an Alph bot.
Why use it?
It gives a bot's decision-making rules a consistent structure and adds labels so strategies can later be found and compared in a strategy directory.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to document a trading approach, define its market and risk categories, and prepare it for use with an Alph bot.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/outsharp/shipp-skills/alph-bot-strategy
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 Outsharp/shipp-skills --skill alph-bot-strategy
Clone the repo
git clone --depth 1 https://github.com/Outsharp/shipp-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 alph-bot-strategy

README.md
[![agentmods](https://agentmods.dev/badge/skills/outsharp/shipp-skills/alph-bot-strategy.svg)](https://agentmods.dev/skills/outsharp/shipp-skills/alph-bot-strategy)
Your own site
<a href="https://agentmods.dev/skills/outsharp/shipp-skills/alph-bot-strategy"><img src="https://agentmods.dev/badge/skills/outsharp/shipp-skills/alph-bot-strategy.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 2,773 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 $0.00000 $0.02773
Opus 5 $0.00000 $0.01386
Sonnet 5 $0.00000 $0.00555
Haiku 4.5 $0.00000 $0.00277

Measured 7d ago against content hash 9f06ac505e0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

alph-bot-strategy 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 7d 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/alph-bot-strategy/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to Create Strategy

This skill helps you write effective STRATEGY.md files for Alph trading bots.

SOUL.md defines who the bot is. STRATEGY.md defines how it thinks. This skill teaches you how to write the thinking.

Strategy Discoverability

Coming soon — The Alph.bot Strategy Registry is under development. The tagging system below is forward-compatible and will be indexed when the directory launches.

Every STRATEGY.md should define tags in a metadata block at the top of the file. These tags allow the strategy to be found, filtered, and recommended in the Alph.bot Strategy Directory — a community-maintained catalog of strategies that users can browse, fork, and deploy.

Required metadata block (place at the very top of STRATEGY.md):

---
name: "Vanilla Value Hunter"
author: "Joe"
tags: [nba, prediction-markets, polymarket, injury-news, live-betting, value-betting]
market: [prediction-markets]
asset: [nba]
risk_profile: conservative
version: 1
---

Tag guidelines:

  • Use lowercase, hyphenated tags
  • Include market type, asset class, specific platform, and edge type
  • Add descriptive tags for the core thesis (e.g., momentum-lag, injury-mispricing, sentiment-overreaction)
  • risk_profile accepts: conservative, moderate, aggressive
  • The more specific the tags, the easier it is for other hunters to find and build on your work

When the Strategy Directory launches, users will be able to search by tag, filter by market and risk profile, and see community ratings and performance metrics for published strategies.

Architecture

A STRATEGY.md has five sections. Each one builds on the last.

1. Tools & Skills

What the bot has access to. Data feeds, APIs, execution tools, analysis capabilities. Be specific — list every tool by name and describe when to use it.

The bot can only act on what it can see. This section defines its senses.

What belongs here:

  • Real-time data APIs (e.g., Shipp NBA play-by-play, odds feeds, injury reports)
  • Market execution tools (e.g., Polymarket API, exchange connectors)
  • Analysis tools (e.g., statistical models, sentiment scrapers)
  • When to use each tool and what to expect back

Read the full file on GitHub · 237 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. 7d ago First seen · 237 lines · 0 tokens per session scan A 9f06ac505e0b

Subscribe to this mod's changes

alph-bot-strategy is a skill published in the GitHub repository Outsharp/shipp-skills (4 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,773 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.

Related

Other skills, from other repositories