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.
npx agentmods add commands/mrjptech/macro-pickle/pickle-ugcgit clone --depth 1 https://github.com/MrJPTech/macro-pickleWrote 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.
[](https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-ugc)<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-ugc"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-ugc.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00040 | $0.00791 |
| Opus 5 | $0.00020 | $0.00396 |
| Sonnet 5 | $0.00008 | $0.00158 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
pickle-ugc 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pickle-ugc
Build faceless short-form UGC that sells a product — the selling layer over the
Prompt Engine (scripts/lib/prompts/ugc.ts). Methodology: content/knowledge/PROMPT-COOKBOOK.md
§14. Selling craft: the ugc-shortform-prompting skill.
Exported prompts go to the vault
Finalized prompts are saved to your prompt vault as copy-paste Obsidian markdown via
exportPromptToVault (the pack script does this for every product). Do not hand-roll a
different format. Destination override: MACRO_PICKLE_PROMPT_VAULT.
The one rule: faceless
Product + hands + on-screen captions + music/VO — no face in frame. It's the house format and it removes identity-lock / IP cost. Hook the product in the first 3 seconds.
Usage
-
Parse
$ARGUMENTS. Identify the product, the--format(defaultfaceless-finds; alsounboxing,problem-solution,demo,before-after,listicle,tutorial), and whether a real photo is involved. -
(Optional) Parse a real supplier photo — OCR foreign text + get an in-use scene:
pnpm describe --image <photo> --brand "Quiet Desk Co. (premium desk objects)" -
Build the spot via the MCP
build_ugc_spottool (orbuildUgcSpotfromscripts/lib/prompts/ugc.ts), passing the product id, name, benefit verb-phrase, scene, and--format. Setsave: trueto write the notes.For a recurring catalog, write a small pack script that holds a
PRODUCTSarray and loopsbuildUgcSpotover it — that keeps ids, benefits, and scenes in one place and makes the whole set re-runnable. -
Each product yields 3 vault notes: clean hero still, faceless lifestyle still, and a 9:16 spot (hook→demo→CTA + caption track). Report the paths.
-
Render pixels (optional, paid): add
--generateto render the stills via Imagen / Nano Banana intoMACRO_PICKLE_EXPORT_DIR. Confirm before any live--generate— it calls a paid Google API. Paste the 9:16 SPOT briefs into Google Flow / Veo; burn captions in post.
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.
- 4d ago First seen · 54 lines · 40 tokens per session scan A 4d85d3a15fd8
pickle-ugc is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 791 once invoked, about $0.0002 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.
Other commands, from other repositories
media-extract-frames
Gemini-only command that identifies visually significant video frames and describes each as a storyboard entry.
stt
Transcribe a local audio file or remote audio URL into text.
brand-generate
Generate an on-brand document from a saved Brand Profile.
audition-voices
Generate voice audition samples for a character using Venice TTS.
list
List available Piper TTS TTS voices with optional filtering.
review-video
Make a " Reviews" video — a fast, faceless VO montage of REAL, verified competitor reviews that names the recurring complaints and positions YOUR business as the alternative, then hands off to your own customer testimonials.