broker-card

broker-card is a skill for Claude Code from madguyevans-creator/resale-agent-skill-hub. It costs 78 tokens per session (610 once invoked), scanned A, original, MIT.

A tool for preparing and publishing item listings on consumer-to-consumer (C2C) marketplaces. It creates a separate listing card for each platform and publishes only after you confirm it.

In plain words
What is it for?
Use it after researching an item's price to create platform-specific titles, categories, descriptions, tags, and prices, then set price rules and publish the listings.
Why use it?
It removes the need to rewrite listing details for every marketplace. It also prevents publishing until a minimum price and repricing schedule are set.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the resale-agent-skill-hub plugin — 8 skills shipped together

Good fit Use it after researching an item's price to create platform-specific titles, categories, descriptions, tags, and prices, then set price rules and publish the listings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/madguyevans-creator/resale-agent-skill-hub/broker-card
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 madguyevans-creator/resale-agent-skill-hub --skill broker-card
Clone the repo
git clone --depth 1 https://github.com/madguyevans-creator/resale-agent-skill-hub

Made for: Claude Code.

Or install resale-agent-skill-hub, the plugin that ships this one along with the rest of its 8 skills.

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 broker-card

README.md
[![agentmods](https://agentmods.dev/badge/skills/madguyevans-creator/resale-agent-skill-hub/broker-card/github.svg)](https://agentmods.dev/skills/madguyevans-creator/resale-agent-skill-hub/broker-card)
Your own site
<a href="https://agentmods.dev/skills/madguyevans-creator/resale-agent-skill-hub/broker-card"><img src="https://agentmods.dev/badge/skills/madguyevans-creator/resale-agent-skill-hub/broker-card/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 broker-card

Your own site · 80×15
<a href="https://agentmods.dev/skills/madguyevans-creator/resale-agent-skill-hub/broker-card"><img src="https://agentmods.dev/badge/skills/madguyevans-creator/resale-agent-skill-hub/broker-card.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 610 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 $0.00078 $0.00610
Opus 5 $0.00039 $0.00305
Sonnet 5 $0.00016 $0.00122
Haiku 4.5 $0.00008 $0.00061

Measured 11d ago against content hash bb3e28b435a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

broker-card 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/publish.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/broker-card/SKILL.md · 57 lines

What it actually says

broker-card: Generate, Review, and Publish Listings

Generates platform-specific listing cards, collects schedule+fuse settings, and auto-publishes on user confirmation.

Workflow

Phase 1: Card Generation

For each target platform, generate a formatted listing card:

┌─────────────────────────────────────┐
│ 🛍️  闲鱼 Xianyu 上架卡片            │
├─────────────────────────────────────┤
│  📝 标题: [platform-optimized]      │
│  📂 分类: [platform category path]  │
│  💰 价格: ¥XXX                      │
│  📋 描述: [platform-tone adapted]   │
│  🏷️  标签: #tag1 #tag2 #tag3       │
│  ⚠️  成色: Grade X — [detail]      │
└─────────────────────────────────────┘

Phase 2: Schedule + Shield (MANDATORY before publishing)

  • Price shield: Unbreachable floor price. This MUST be set via broker-fuse before publishing. The publish script validates: if no floor is set, publishing is blocked.
  • Repricing interval: How often to re-check prices (default 7 days)

Explain the trade-off: higher floor = more profit per sale but slower; lower floor = faster liquidity.

Phase 3: Publish (floor-gated)

  • Floor validation: script checks listing.fuse_price > 0 and listing.current_price >= listing.fuse_price. Blocked otherwise.
  • User says "发布" or "confirm"
  • Script auto-publishes to each platform using stored session
  • Each publish event is logged to the audit trail (audit_logger.log_publish)
  • Each listing URL is saved to state manager
  • System scheduler is registered for repricing checks

Platform Adaptations

Platform Tone Title Limit
闲鱼 Xianyu Casual, authentic, community 30 chars
转转 Zhuanzhuan Semi-formal, inspection-report 40 chars
eBay Professional, keyword-dense 80 chars
Depop Lifestyle, aesthetic 60 chars

Script

python3 scripts/publish.py --item-id <id> --action generate  # Generate cards
python3 scripts/publish.py --item-id <id> --action publish   # Publish all
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. 11d ago First seen · 57 lines · 0 tokens per session scan A bb3e28b435a0

Subscribe to this mod's changes

broker-card is a skill published in the GitHub repository madguyevans-creator/resale-agent-skill-hub (94 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 610 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories