What makes fleece notable?

1.4K downloads. Trust evidence available

How should fleece be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

fleece

Credit card research and redemption CLI. Looks up rewards rates, annual fees, welcome bonuses, statement credits, transfer partners, point valuations, application rules, lounge access, and travel protections for Chase, Amex, Citi, Capital One, Bilt, and all major US issuers. Compare cards, analyze wallet gaps, estimate ROI, get recommendations, look up merchant category codes, and search award flights and hotels. Install with pip install fleece-cli. Skill: fleece Owner: chenyuan99 Summary: Credit card research and redemption CLI. Looks up rewards rates, annual fees, welcome bonuses, statement credits, transfer partners, point valuations, application rules, lounge access, and travel protections for Chase, Amex, Citi, Capital One, Bilt, and all major US issuers. Compare cards, analyze wallet gaps, estimate ROI, get recommendations, look up merchant category codes,

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.4k

Updated

Oct 10, 2026

Version

1.6.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.4K downloadsadoption · observed Oct 10, 2026
Latest release: 1.6.1release · observed Aug 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17ej20pbgf1t4n63yvq27gzh183fzvq:fleece

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chenyuan99-fleece/snapshot"

Documentation

CLAWHUB

149,812 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: fleece
description: Credit card research and redemption CLI. Looks up rewards rates, annual fees, welcome bonuses, statement credits, transfer partners, point valuations, application rules, lounge access, and travel protections for Chase, Amex, Citi, Capital One, Bilt, and all major US issuers. Compare cards, analyze wallet gaps, estimate ROI, get recommendations, look up merchant category codes, and search award flights and hotels. Install with pip install fleece-cli.
metadata:
  author: chenyuan99
  version: "1.6.0"
---

# Fleece — Credit Card Research & Redemption

Use this skill when the user asks about:
- **Specific cards**: "What are the Amex Gold benefits?", "Is the Chase Sapphire Preferred worth it?", "What changed with the Citi Double Cash?"
- **Earning rates**: "Which card earns the most on dining?", "What's the best card for groceries?"
- **Transfer partners**: "Where can I transfer Chase Ultimate Rewards?", "What airlines does Amex transfer to?", "Do Bilt points transfer to Hyatt?"
- **Point valuations**: "How much are Chase UR points worth?", "Best way to redeem Amex MR?", "What CPP can I get from Hyatt?", "Is it worth transferring to Flying Blue?"
- **Application rules**: "What is Chase 5/24?", "Can I get the Sapphire bonus again?", "Am I eligible for the Amex Gold offer?", "How long before I can apply for Citi again?", "Does the Amex once-per-lifetime rule apply here?"
- **Lounge access**: "Which cards get me into Centurion Lounges?", "Does Venture X include Priority Pass?", "Best card for airport lounge access?", "Can I bring guests to Chase Sapphire Lounges?"
- **Travel protections**: "Does Sapphire Reserve cover rental cars?", "What trip delay coverage does Amex Platinum have?", "Which card has the best travel insurance?", "Does Freedom Flex have cell phone protection?"
- **Statement credits**: "How do I use the Amex Gold dining credit?", "What credits does the Venture X have?"
- **Wallet optimization**: "Which card should I use for travel?", "What gaps does my wallet have?"
- **Card recommendations**: "Best travel credit card for beginners", "No annual fee cash back card"
- **ROI / value**: "Is the Amex Platinum worth the $695 fee?", "First-year value of the Sapphire Preferred"
- **Award redemptions**: "Find business class flights JFK to Tokyo", "Search hotels in Paris with points"
- **Merchant lookup**: "What card should I use at Costco?", "Which card earns the most at gas stations?", "What MCC is a pharmacy?"
- **Spending profile**: "Set up my profile", "Save my spending habits", "Remember I spend $600/month on dining", "My preferred airline is United MileagePlus"

Live US credit card data via Brave Search. All commands output JSON for programmatic use.

## Spending profile

The user's spending profile is stored in `fleece.db` and automatically injected into `fleece wallet`, `fleece roi`, and `fleece recommend`. Set it up once and research commands become personalised.

```bash
# Set profile fields (no API key neede

skills/fleece-gmail-spend/SKILL.md

---
name: fleece-gmail-spend
description: Analyze purchase receipts, order confirmations, travel bookings, subscriptions, and refund emails in a connected Gmail account to estimate spending habits, then compare those habits with cards saved in the Fleece wallet. Use for Gmail-based consumption analysis, spend-category summaries, card-position reviews, missed-rewards estimates, wallet coverage gaps, best-card-by-category guidance, and proposed Fleece spending-profile updates.
---

# Fleece Gmail Spend

Combine read-only Gmail evidence with Fleece wallet data to show how well the user's current cards fit actual spending. Treat email-derived totals as estimates, not a bank-statement substitute.

## Workflow

1. Establish the analysis window. Use the user's dates; otherwise analyze the most recent 90 days and state that scope.
2. Read the current Fleece position before recommending changes:
```bash
fleece cards list --json
fleece profile show --json
```
3. Search Gmail for transaction evidence. Prefer Gmail-native search, then batch-read shortlisted messages. Start with queries such as:
```text
newer_than:90d (subject:(receipt OR order OR purchase OR invoice) OR from:(uber.com doordash.com instacart.com amazon.com))
newer_than:90d (subject:(booking OR itinerary OR reservation) OR from:(airbnb.com expedia.com))
newer_than:90d subject:(refund OR refunded OR cancellation)
```
Adapt merchant and issuer terms to the mailbox. Search broad categories separately when one query would truncate coverage.
4. Extract only the transaction date, merchant, amount, currency, likely category, order status, and source message ID. Do not expose full message bodies or unrelated personal data.
5. Normalize and deduplicate:
- Count the final charged total once, not order, shipping, and delivery updates separately.
- Subtract confirmed refunds and exclude canceled orders.
- Separate taxes, tips, and fees only when clearly itemized; otherwise retain the final total.
- Keep non-USD transactions separate unless a reliable conversion amount appears in the email.
- Exclude marketing offers, reward summaries, balance notices, and statements that duplicate itemized receipts.
6. Classify spending into Fleece profile categories: dining, groceries, travel, gas, and other. Mark uncertain classifications and avoid inventing MCCs. Use `fleece mcc <code> --wallet --json` only when an MCC is explicitly present.
7. Calculate monthly estimates using only covered days. Report total captured spend, monthly average, category share, recurring merchants or subscriptions, and evidence coverage.
8. Compare the observed mix with current cards:
```bash
fleece wallet --json
```
If `BRAVE_API_KEY` is unavailable, use saved card reward metadata and label the comparison partial. Do not guess current benefits or annual fees.
9. Identify the best current card for each observed category, weak or overlapping coverage, explicit card misuse, and conserv

skills/fleece/SKILL.md

---
name: fleece
description: Credit card research and redemption CLI. Looks up rewards rates, annual fees, welcome bonuses, statement credits, transfer partners, point valuations, application rules, lounge access, and travel protections for Chase, Amex, Citi, Capital One, Bilt, and all major US issuers. Compare cards, analyze wallet gaps, estimate ROI, get recommendations, look up merchant category codes, and search award flights and hotels. Install with pip install fleece-cli.
metadata:
  author: chenyuan99
  version: "1.6.0"
---

# Fleece — Credit Card Research & Redemption

Use this skill when the user asks about:
- **Specific cards**: "What are the Amex Gold benefits?", "Is the Chase Sapphire Preferred worth it?", "What changed with the Citi Double Cash?"
- **Earning rates**: "Which card earns the most on dining?", "What's the best card for groceries?"
- **Transfer partners**: "Where can I transfer Chase Ultimate Rewards?", "What airlines does Amex transfer to?", "Do Bilt points transfer to Hyatt?"
- **Point valuations**: "How much are Chase UR points worth?", "Best way to redeem Amex MR?", "What CPP can I get from Hyatt?", "Is it worth transferring to Flying Blue?"
- **Application rules**: "What is Chase 5/24?", "Can I get the Sapphire bonus again?", "Am I eligible for the Amex Gold offer?", "How long before I can apply for Citi again?", "Does the Amex once-per-lifetime rule apply here?"
- **Lounge access**: "Which cards get me into Centurion Lounges?", "Does Venture X include Priority Pass?", "Best card for airport lounge access?", "Can I bring guests to Chase Sapphire Lounges?"
- **Travel protections**: "Does Sapphire Reserve cover rental cars?", "What trip delay coverage does Amex Platinum have?", "Which card has the best travel insurance?", "Does Freedom Flex have cell phone protection?"
- **Statement credits**: "How do I use the Amex Gold dining credit?", "What credits does the Venture X have?"
- **Wallet optimization**: "Which card should I use for travel?", "What gaps does my wallet have?"
- **Card recommendations**: "Best travel credit card for beginners", "No annual fee cash back card"
- **ROI / value**: "Is the Amex Platinum worth the $695 fee?", "First-year value of the Sapphire Preferred"
- **Award redemptions**: "Find business class flights JFK to Tokyo", "Search hotels in Paris with points"
- **Merchant lookup**: "What card should I use at Costco?", "Which card earns the most at gas stations?", "What MCC is a pharmacy?"
- **Spending profile**: "Set up my profile", "Save my spending habits", "Remember I spend $600/month on dining", "My preferred airline is United MileagePlus"

Live US credit card data via Brave Search. All commands output JSON for programmatic use.

## Spending profile

The user's spending profile is stored in `fleece.db` and automatically injected into `fleece wallet`, `fleece roi`, and `fleece recommend`. Set it up once and research commands become personalised.

```bash
# Set profile fields (no API key neede

ios/README.md

# Fleece iOS App

Native SwiftUI iPhone app that:

1. Tracks your location with CoreLocation
2. Uses **Apple MapKit `MKLocalSearch`** (free, no API key) to identify the store you're in
3. Maps `MKPointOfInterestCategory` → **MCC category** (dining, groceries, gas, hotels, etc.)
4. Ranks all cards by effective reward rate for that category
5. Fires a **local push notification**: *"Use Amex Gold · 4x Dining = 7.2% back (Amex MR)"*

**Zero per-request cost.** All place lookups stay on-device via Apple's MapKit framework.

---

## Setup

No API keys needed. Just:

1. Open Xcode → create a new **iOS App** project
   - Product Name: `FleeceApp`
   - Interface: **SwiftUI** / Language: **Swift**
   - Bundle ID: `io.getfleece.app`

2. Drag all `.swift` files from this directory into the Project Navigator (preserving folder groups)

3. Replace the generated `Info.plist` with the one in this directory

4. Under **Signing & Capabilities**, add:
   - **Background Modes → Location updates** (optional, for background detection)

5. Build and run on a physical device (CoreLocation requires real hardware)

---

## Architecture

```
FleeceApp/
├── FleeceApp.swift          — App entry; requests location + notification permissions
├── ContentView.swift        — TabView: Home / Wallet / Settings
├── AppState.swift           — Central @ObservableObject: orchestrates search + wallet
├── Config.swift             — Detection radius, notification cooldown constants
│
├── Views/
│   ├── HomeView.swift               — MapKit map + current place banner + card scroll
│   ├── RecommendationCardView.swift — Horizontal card chips + full recommendations sheet
│   ├── WalletView.swift             — Add/remove cards from wallet
│   └── SettingsView.swift           — App info (no API key needed)
│
├── Managers/
│   ├── LocationManager.swift     — CLLocationManager wrapper (@MainActor)
│   ├── PlacesService.swift       — MKLocalSearch wrapper (free, actor)
│   └── NotificationManager.swift — UNUserNotificationCenter, 5-min cooldown
│
├── Models/
│   ├── MCCCategory.swift   — MKPointOfInterestCategory → MCC mapping
│   ├── CreditCard.swift    — Card model + Color(hex:) extension
│   ├── NearbyPlace.swift   — Place model + MKMapItem conversion
│   └── Recommendation.swift — Ranked recommendation result
│
└── Services/
    ├── CardDatabase.swift   — 9 hard-coded US cards (Chase, Amex, Citi, CapOne, Bilt)
    └── CardRecommender.swift — Sorts cards by effective rate, wallet cards first
```

## MKPointOfInterestCategory → MCCCategory Mapping

| MCCCategory | MKPointOfInterestCategory values |
|---|---|
| Dining | restaurant, cafe, bakery, brewery, winery, nightlife |
| Groceries | foodMarket |
| Gas | gasStation |
| Hotels | hotel |
| Flights | airport |
| Transit | publicTransport |
| Drugstore | pharmacy |
| Entertainment | movieTheater, stadium, musicVenue, amusementPark, bowling, zoo, aquarium |
| Shopping | store, clothing |

## Card Database (9 cards)

| Card | Top Category | Effect

README.md

# Fleece — Credit Card Research & Redemption

[![PyPI version](https://img.shields.io/pypi/v/fleece-cli?color=FFD100&label=fleece-cli)](https://pypi.org/project/fleece-cli/)
[![PyPI downloads](https://img.shields.io/pypi/dm/fleece-cli?color=FFD100)](https://pypi.org/project/fleece-cli/)
[![Python](https://img.shields.io/pypi/pyversions/fleece-cli?color=FFD100)](https://pypi.org/project/fleece-cli/)
[![License: MIT](https://img.shields.io/badge/License-MIT-FFD100.svg)](https://github.com/chenyuan99/fleece/blob/main/LICENSE)
[![Publish to PyPI](https://github.com/chenyuan99/fleece/actions/workflows/publish.yml/badge.svg)](https://github.com/chenyuan99/fleece/actions/workflows/publish.yml)
[![ClawHub](https://img.shields.io/badge/ClawHub-fleece%401.5.0-FFD100)](https://clawhub.ai)
[![Website](https://img.shields.io/website?url=https%3A%2F%2Fgetfleece.io&color=FFD100&label=getfleece.io)](https://getfleece.io/)

> Find the best card for deal saviors.

Fleece is a free, open-source credit card research and award redemption toolkit. It provides live data via Brave Search — no stale training data. Every command outputs clean JSON, making it easy to plug into AI agent workflows.

---

## Quick Start

```bash
pip install fleece-cli
export BRAVE_API_KEY=<your_key>   # optional — offline commands work without it

fleece card "Amex Gold"           # full card report
fleece wallet                     # portfolio analysis
fleece mcc 5812                   # MCC lookup (no API key needed)
fleece flights JFK NRT --date 2026-06-01 --cabin business --open
```

### Install as an agent skill (55+ agents)

```bash
npx skills add chenyuan99/fleece
```

Works with Claude Code, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, Codex, Warp, Kiro, and more — all from one command.

## CLI Commands

### Research (requires `BRAVE_API_KEY`)

| Command | Description |
|---|---|
| `fleece card "<name>"` | Fees, welcome offer, earning rates, credits, benefits |
| `fleece rates "<name>"` | Earning rates by spend category |
| `fleece partners "<name>"` | Transfer partners, ratios, and timing |
| `fleece credits "<name>"` | Statement credits and perks |
| `fleece news "<name>"` | Recent changes (past month) |
| `fleece compare "<A>" "<B>"` | Side-by-side card comparison |
| `fleece wallet` | Portfolio analysis — coverage, overlaps, gaps |
| `fleece roi "<name>"` | First-year ROI estimate |
| `fleece recommend "<profile>"` | Personalized card recommendations |

### Offline (no API key needed)

| Command | Description |
|---|---|
| `fleece mcc <code>` | Look up a Merchant Category Code (981 codes bundled) |
| `fleece mcc <code> --wallet` | Cross-reference MCC with your saved cards |
| `fleece flights <ORIGIN> <DEST> --date <YYYY-MM-DD>` | PointsYeah award flight search URL |
| `fleece hotels "<location>" --checkin <date> --checkout <date>` | PointsYeah award hotel search URL |
| `fleece profile set <field> <value>` | Save your spending profile |
| `fleece profile show` | View your

Github ReposUpdated 21h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.