howp
v0.1.1Personal probability dashboard: interests → measurable questions → prediction-market probabilities (Polymarket, Manifold) → a local dashboard of what became more or less likely. The skill reads this package's binaries.json, downloads the released archive for the host platform, verifies it against the sha256 recorded there before unpacking it, caches it under the user's home, and then drives the six binaries. Only aarch64-apple-darwin is published, and the skill says so and stops on any other platform. No API keys and no accounts. Deterministic work — market calls, storage, arithmetic, move detection, rendering — is the binaries'; every step that needs judgement is performed by the agent running the skill, between a binary's plan command and its apply command. No binary invokes a model.
By Alexander KurganovLicense: MIT0 GitHub starsUpdated 8 hours ago
Directory evidence
- Runtimes
- Claude Code and Agent Plugins
- Parsed components
- 1 skill or MCP entry
- Source updated
- Aug 26, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install plugin
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install howp@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/Akurganow/ai-pluginsClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/howp/.
Plugin files
├── .claude-plugin/plugin.json├── plugin.json└── skills/howp/SKILL.md
Included Skills1
A personal probability dashboard. Turns what someone follows into measurable questions, matches those questions to prediction markets (Polymarket, Manifold), records the probabilities over time, detects sharp moves, and renders a local dashboard of what became more or less likely. Use when the user asks to set up, run or refresh a howp workspace, collect market probabilities for their questions, check that a market really answers a question, find sharp probability moves, explain a move from the news, or write the weekly digest. macOS on Apple Silicon only — the published binaries are aarch64-apple-darwin and this skill stops on any other platform. No API keys. Every step that needs judgement is performed by you, the agent, between a binary's `plan` command and its `apply` command: the binaries never call a model.
Plugin manifests2
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "howp",
"version": "0.1.1",
"description": "Personal probability dashboard: interests → measurable questions → prediction-market probabilities (Polymarket, Manifold) → a local dashboard of what became more or less likely. The skill reads this package's binaries.json, downloads the released archive for the host platform, verifies it against the sha256 recorded there before unpacking it, caches it under the user's home, and then drives the six binaries. Only aarch64-apple-darwin is published, and the skill says so and stops on any other platform. No API keys and no accounts. Deterministic work — market calls, storage, arithmetic, move detection, rendering — is the binaries'; every step that needs judgement is performed by the agent running the skill, between a binary's plan command and its apply command. No binary invokes a model.",
"author": {
"name": "Alexander Kurganov",
"url": "https://github.com/Akurganow"
},
"homepage": "https://github.com/Akurganow/ai-plugins/tree/main/plugins/howp",
"repository": "https://github.com/Akurganow/ai-plugins",
"license": "MIT",
"keywords": [
"probability",
"forecasting",
"prediction-markets",
"polymarket",
"manifold",
"dashboard",
"agent-skills"
]
}{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "howp",
"version": "0.1.1",
"description": "Personal probability dashboard: interests → measurable questions → prediction-market probabilities (Polymarket, Manifold) → a local dashboard of what became more or less likely. The skill reads this package's binaries.json, downloads the released archive for the host platform, verifies it against the sha256 recorded there before unpacking it, caches it under the user's home, and then drives the six binaries. Only aarch64-apple-darwin is published, and the skill says so and stops on any other platform. No API keys and no accounts. Deterministic work — market calls, storage, arithmetic, move detection, rendering — is the binaries'; every step that needs judgement is performed by the agent running the skill, between a binary's plan command and its apply command. No binary invokes a model.",
"author": {
"name": "Alexander Kurganov",
"url": "https://github.com/Akurganow"
},
"homepage": "https://github.com/Akurganow/ai-plugins/tree/main/plugins/howp",
"repository": "https://github.com/Akurganow/ai-plugins",
"license": "MIT",
"keywords": [
"probability",
"forecasting",
"prediction-markets",
"polymarket",
"manifold",
"dashboard",
"agent-skills"
]
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[howp on Agent Plugins Marketplace](https://pluginsmp.com/plugins/howp)