pickle-pipeline

pickle-pipeline is a command for Claude Code from MrJPTech/macro-pickle. It costs 22 tokens per session (1,048 once invoked), scanned A, original, MIT.

A local media workflow that turns a rough scene idea into reference images and then video. It creates candidate frames, lets a person choose which ones to keep, and uses the selected frames for the next stage.

In plain words
What is it for?
Use it to create a scene recipe, generate reference frames, select the best ones, analyze them, and produce video files in a scene-specific output folder.
Why use it?
It organizes image and video generation into repeatable stages without requiring a database.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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-pipeline
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-pipeline

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-pipeline.svg)](https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-pipeline)
Your own site
<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-pipeline"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-pipeline.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,048 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 $0.00022 $0.01048
Opus 5 $0.00011 $0.00524
Sonnet 5 $0.00004 $0.00210
Haiku 4.5 $0.00002 $0.00105

Measured 6d ago against content hash 29671501c6ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pickle-pipeline 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 6d 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-pipeline.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pickle-pipeline

Run the macro-pickle reference → video media pipeline: a two-stage, local, Supabase-free flow that turns a rough idea into reference frames (Nano Banana), lets you curate the keepers, then re-prompts those into video (Veo 3.1). Everything writes to pipeline-output/<scene-slug>/; there is no database.

Replaces the old Supabase content-enrichment pipeline (translate → generate-images → generate, pickle.* tables, sync-approved-to-supabase), which was removed with the CMS scaffold on 2026-06-29 (commit 2b1f250). The code now lives in scripts/pipeline/*.ts + scripts/lib/pipeline/*.ts on the toolkit clients.

Stages

  1. scene:newpnpm scene:new <slug> → scaffold pipeline-output/<slug>/scene.json (the recipe card: prompts + settings + a log of every file made).
  2. scene:refspnpm scene:refs <slug>Stage 1: the prompt enhancer rewrites your idea, then Nano Banana generates MANY candidate reference frames into pipeline-output/<slug>/references/.
  3. curate (human gate)pnpm scene:select <slug> <ids> → YOU pick the keeper frame ids that advance to video.
  4. scene:analyzepnpm scene:analyze <slug> → the vision analyzer "looks at" the keepers and grounds what it sees into the video prompt.
  5. scene:videopnpm scene:video <slug>Stage 2: the keepers become video (Veo 3.1) as ingredients / first-last frames, written to pipeline-output/<slug>/video/.

The curation gate (why this isn't one button)

Stages 1–2 automate; stage 3 (select) needs you to eyeball the candidates and choose ids. So this command runs new → refs, then STOPS for curation. Re-invoke with --from analyze (after pnpm scene:select) to finish analyze → video.

Arguments

$ARGUMENTS:

  • <scene-slug> — required; the scene folder name.
  • --from <stage> — resume at refs | analyze | video (e.g. after curating).
  • --dry-run — print the enhanced prompt + planned commands without spending.

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 22 tokens per session scan A 29671501c6ae

Subscribe to this mod's changes

pickle-pipeline is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,048 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.