pickle-prompt

pickle-prompt is a command for Claude Code from MrJPTech/macro-pickle. It costs 25 tokens per session (731 once invoked), scanned A, original, MIT.

A command that turns a rough image or video idea into a structured prompt for an image or video model.

In plain words
What is it for?
Use it to prepare image prompts, video director briefs, brand-specific prompts, and copy-ready entries in an Obsidian prompt vault.
Why use it?
It helps turn an incomplete idea into a prompt that can be used consistently, and lets you save finalized prompts for later reuse.

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-prompt
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-prompt

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-prompt.svg)](https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-prompt)
Your own site
<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-prompt"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-prompt.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 731 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 $0.00025 $0.00731
Opus 5 $0.00013 $0.00365
Sonnet 5 $0.00005 $0.00146
Haiku 4.5 $0.00003 $0.00073

Measured 6d ago against content hash 927a1547d2df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pickle-prompt 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-prompt.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pickle-prompt

Turn a rough idea into an engineered prompt using the Prompt Engine (scripts/lib/prompts/) and the methodology in content/knowledge/PROMPT-COOKBOOK.md. Image prompts use the Nano Banana "Perfect Prompt" formula; video prompts use the Seedance/Veo "Director Brief".

PROJECT RULE — exported prompts go to the vault

When a prompt is finalized/exported (the user wants to keep or use it), it must be saved into your prompt vault as Obsidian-flavored markdown laid out for copy-paste (the prompt body in a fenced text block). Two ways, both already implemented — do not hand-roll a different format:

  • CLI: append --save (and optionally --title "…") → exportPromptToVault writes to $MACRO_PICKLE_PROMPT_VAULT/<brand>/ (default ./exported-prompts/<brand>/).
  • MCP: pass save: true to build_image_prompt / build_video_prompt.

Destination override: MACRO_PICKLE_PROMPT_VAULT. A dry build (no --save) is fine for iterating; the moment it's the keeper, save it.

Usage

  1. Parse $ARGUMENTS. Decide --image (default) or --video, and whether a --brand is named (list the installed profiles with pnpm prompt --brands).
  2. Turn the idea into a brief. If the user gave prose, map it onto the brief fields (image: subject/action/context/composition/lighting/style/text; video: scene/subject/camera/beats/audio/pacing/intent). Apply cookbook rules: full sentences, exact text in quotes, IP-safe proxies, single-beat pacing, consistency clause for recurring characters.
  3. Build it:
    pnpm prompt --image --brand <brand> --json '<ImageBrief>'
    pnpm prompt --video --brand <brand> --json '<VideoBrief>'
    
  4. Show the result for review.
  5. On approval / "save it" / "export": re-run with --save --title "<name>" (or just add --save). Report the vault path written.
  6. Image generation (optional): add --gen to render the built prompt via Imagen 4.0 into MACRO_PICKLE_EXPORT_DIR (iCloud → phone). This calls a paid Google API — confirm before a live --gen run.

Read the full file on GitHub · 56 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 · 56 lines · 25 tokens per session scan A 927a1547d2df

Subscribe to this mod's changes

pickle-prompt is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 731 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.