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-editgit 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-edit)<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-edit"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-edit.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 | $0.00019 | $0.00974 |
| Opus 5 | $0.00010 | $0.00487 |
| Sonnet 5 | $0.00004 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
pickle-edit 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 3d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pickle-edit
Conversational video generation + editing via pnpm omni (scripts/generate-omni.ts
→ scripts/lib/omni.ts, model gemini-omni-flash-preview). The headline use: take a
reference video, describe the change in plain language ("replace the mug with our box",
"make it golden hour", "remove the watermark person"), get an edited MP4 back. Chain
refinements turn-by-turn with --continue <interaction-id> — no re-describing the scene.
Usage
- Parse
$ARGUMENTSinto apnpm omniinvocation:- Edit a reference clip:
pnpm omni --video "<ref.mp4>" --prompt "<change>" - Generate fresh:
pnpm omni --prompt "<scene>"(add--image <p1,p2>for subject/product lock) - Refine the last result:
pnpm omni --continue <interaction-id> --prompt "<next change>" - Pass through
--aspect 16:9|9:16,--duration <e.g. 8s>,--name,--out,--task.
- Edit a reference clip:
- Prompt quality: for fresh generations, build the prompt with the Prompt Engine
(
--file <brief.json> --brand <name>) or/pickle-promptfirst. For edits, a plain imperative sentence is correct — the model has the source video as context. - Always print the interaction id from the output back to the user — it's the handle for the next conversational edit.
--dry-runprints the prompt + cost estimate without calling the API.
SPEND (paid model — know before you run)
- No free tier (unlike Imagen/Gemini text):
$0.10/second of output video (720p, $17.50/1M tokens at 5792 tok/s). 8s clip ≈ $0.81; each$0.009/s); ref images ~$0.003 each.--continuerefinement is a fresh render at the same rate. Input video is cheap ( - Verified live 2026-07-01 on the project
GOOGLE_API_KEY— generation and multi-turn editing both work on this key. The CLI prints an estimate before every run. - Track monthly spend at https://ai.studio (spend cap applies;
withRetryclassifies cap/quota errors and aborts cleanly).
Model limits (API, 2026-07)
- One reference video max; clips ≤3s misprocess — use ≥4s sources. No audio refs.
- No negative prompts, temperature, or system instructions (the prompt is everything).
- Editing UPLOADED videos is unavailable in EEA/CH/UK (model-generated edits fine).
- Output is SynthID-watermarked. 720p; 16:9 or 9:16.
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.
- 3d ago First seen · 65 lines · 19 tokens per session scan A b9e1c54aec1b
pickle-edit is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 974 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.