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-clipsgit 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-clips)<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-clips"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-clips.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 | $0.00024 | $0.01004 |
| Opus 5 | $0.00012 | $0.00502 |
| Sonnet 5 | $0.00005 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00100 |
Grade A, and why
pickle-clips 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pickle-clips
Batch-generate product clips from a store's gen5 reference sets via pnpm gen-clips
(scripts/gen-clips.ts). Per SKU: 2 Veo ASSET-lock scene variants (FREE) + 1 Kling
studio→lifestyle reveal (paid). Generic — point it at any
<store>/<category>/<sku>/gen5/{studio_01..03,life_01..02}.png layout with a scenes config.
Supabase-free.
Usage
- Parse
$ARGUMENTS—--store <media-dir>is required; pass through--skus / --veo-only / --kling-only / --limit / --model / --aspect / --out / --no-audio / --force. - ALWAYS dry-run first (zero API):
pnpm gen-clips --store <dir> --dry-run→ confirm SKU count, clip count, and Kling cost. - Scenes config — gen-clips loads
content/clip-scenes/<basename(store)>.json(per-category Veo pair + Kling reveal +_scaleper-SKU size anchors + optional_suffixstyle override). If absent it warns and uses generic scenes — author one for a new store by copyingcontent/clip-scenes/example-store.json. - Free pass first:
--veo-only($0). Only run the Kling pass after confirming spend. - The spend gate is ENFORCED: a paid Kling run aborts without
--yes, and aborts if the estimate exceeds--max-spend(default $25, envMACRO_PICKLE_MAX_SPEND_USD). Only add--yesafter the user has confirmed the dry-run cost. - Re-runs are resume-safe: clips whose output already exists are skipped (no double
spend);
--forceregenerates.
SPEND + QUOTA (hard-won — bake into every run)
- Veo is "free" only on the
GOOGLE_API_KEYquota, and the FREE tier is daily-rate-limited (~10 gens/day →429 RESOURCE_EXHAUSTEDwhen tapped). Image quota is SEPARATE (image gen can still work while Veo is tapped). For real volume: Google Flow (Ultra account) or enable billing on the key's GCP project (Veo 3.1 Fast ≈ $0.10/s 720p · $0.12 1080p · default 8s ≈ $0.80–0.96/clip, billed only on success). - Kling = real fal.ai money — 2.6 Pro i2v is $0.14/s with audio ($0.70/5s clip),
$0.07/s without (
--no-audio); verified fal pricing 2026-07, table inscripts/lib/kling.ts. Check the fal.ai balance before a--kling/full run. Confirm with the user before any live paid spend — then pass--yes. - If a Veo daily-quota 429 hits mid-batch, the engine skips the remaining Veo clips automatically (Kling continues); re-run the same command tomorrow to resume.
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 · 60 lines · 24 tokens per session scan A 223f86aa5542
pickle-clips is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,004 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.
Other commands, from other repositories
product-image
Generates professional product photos (3 or 5 shots) from a photo folder or a store URL, in minimalist, elegant or UGC style, with product-fidelity verification.
ebay-analyze
Analyze item photos and identify product details.
package-for-sale
Package a CNC design for selling on Etsy, Cults3D, or Gumroad.
brand-generate
Generate an on-brand document from a saved Brand Profile.
audition-voices
Generate voice audition samples for a character using Venice TTS.
search
Search videos by text, image, or entity using TwelveLabs.