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-charactergit 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-character)<a href="https://agentmods.dev/commands/mrjptech/macro-pickle/pickle-character"><img src="https://agentmods.dev/badge/commands/mrjptech/macro-pickle/pickle-character.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 | $0.00021 | $0.00514 |
| Opus 5 | $0.00010 | $0.00257 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
pickle-character 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.
What it actually says
/pickle-character
Generate a scene with a locked human likeness by feeding real reference photos to nano
(generateWithRefs) so the face/identity stays consistent shot to shot. Uses the
character-lock skill's Visual Anchor workflow (.claude/skills/character-lock/).
This is a generic driver — point it at any character you have rights to. For recurring characters, write a dedicated pack script instead so the reference set and physical description live in one place.
Usage
- Identify the character + its reference photos. Keep a short "character bible" note (physical description, wardrobe, do/don't) next to the photos. Use 2–3 references — front-neutral + smile + jaw/profile gives the strongest lock.
- Read the
character-lockskill for the anchor + redundant-text-anchoring protocol, and copy the character's physical description from the bible into the prompt. - Generate:
pnpm nano --prompt "<scene> — <character physical description from the bible>" \ --refs "<photo1>,<photo2>,<photo3>" --model pro --aspect <ratio> --save - For VIDEO of a real face: route to Veo 3.0 (
veo3) or Google Flow — Veo 3.1 image-to-video filters face-seeded inputs (see the note inscripts/lib/veo.ts).
House rules
- Only lock likenesses you have the right to use — your own, or someone who has given
explicit consent. Do NOT generate real third-party public figures' faces; use a brand
castproxy description instead (also keeps you clear of IP filters). - Faceless product/UGC content doesn't need identity lock — that's /pickle-ugc.
- On finalize,
--saveexports the prompt to your vault. pnpm nano(image) is its own quota — generally available even when Veo is rate-limited.
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 · 40 lines · 21 tokens per session scan A 5e1e7905c6bf
pickle-character is a command published in the GitHub repository MrJPTech/macro-pickle (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 514 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
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.