pickle-winners

pickle-winners is a command for Claude Code from MrJPTech/macro-pickle. It costs 20 tokens per session (449 once invoked), scanned A, original, MIT.

A command that ranks a store's products by their recorded sales count and produces a shortlist for video generation.

In plain words
What is it for?
Use it to rank products, inspect where sales drop off, choose a top group, and export product IDs for a later clip-generation command.
Why use it?
It helps focus video work on products with demonstrated demand instead of processing every product.

Command for Claude Code

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 commands/mrjptech/macro-pickle/pickle-winners
Clone the repo
git clone --depth 1 https://github.com/MrJPTech/macro-pickle

Made for: Claude Code.

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 pickle-winners

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-winners.svg)](https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-winners)
Your own site
<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-winners"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-winners.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00020 $0.00449
Opus 5 $0.00010 $0.00225
Sonnet 5 $0.00004 $0.00090
Haiku 4.5 $0.00002 $0.00045

Measured 5d ago against content hash e128d4372544, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

pickle-winners 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.

.claude/commands/pickle-winners.md · 31 lines

What it actually says

/pickle-winners

Rank a store's SKUs by SALES (the 1688 booked-count demand signal) via pnpm rank-skus (scripts/rank-skus.ts) so a generation run targets the proven winners instead of every SKU. Read-only, zero API calls — always safe to run.

Usage

  1. Rank: pnpm rank-skus --store <media-dir> --top <N> → a ranked table (clip-ready gen5 SKUs only by default; add --all to include SKUs with no gen5 set). --store is required (or set MACRO_PICKLE_STORE_DIR).
  2. Read the elbow: there's usually a clear sales drop-off — recommend the cut to the user (e.g. "top 8 = the Pareto winners") rather than an arbitrary N.
  3. Hand off to clips: pnpm rank-skus --store <dir> --top <N> --ids → CSV of winner SKU ids → pnpm gen-clips --store <dir> --skus <csv> (or run /pickle-clips with that --skus).

Notes

  • Demand signal = manifest.json sales per offerId. Requires the store dir to contain manifest.json + <category>/<sku>/gen5/.
  • --json for machine output; --ids for the bare CSV (the pipe to gen-clips --skus).
  • This is the front half of the money loop: rank winners → /pickle-clips → cull in edit → post. It does not spend anything; the spend gate lives in /pickle-clips.
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 · 31 lines · 20 tokens per session scan A e128d4372544

Subscribe to this mod's changes

pickle-winners is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 449 once invoked, about $0.0001 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 2026-08-31.