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 skills add palmier-io/palmier-skills --skill character-pipelinegit clone --depth 1 https://github.com/palmier-io/palmier-skillsWrote 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/skills/palmier-io/palmier-skills/character-pipeline)<a href="https://agentmods.dev/skills/palmier-io/palmier-skills/character-pipeline"><img src="https://agentmods.dev/badge/skills/palmier-io/palmier-skills/character-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/palmier-io/palmier-skills/character-pipeline"><img src="https://agentmods.dev/badge/skills/palmier-io/palmier-skills/character-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00104 | $0.01414 |
| Opus 5.5 | $0.00042 | $0.00566 |
| Sonnet 5.5 | $0.00021 | $0.00283 |
| Haiku 4.5 | $0.00010 | $0.00141 |
Grade A, and why
character-pipeline 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 2mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character Pipeline
This skill is stills-only. It builds reusable identity assets so the same person holds across plates and composites. If the user wants motion after that, hand off the approved scene still + sheets to video-prompting / cinematic-motion — do not own generate_video here.
Pipeline (hard order)
1. Hero still generate_image (or import_media / user photo)
2. Multi-angle sheet generate_image with referenceMediaRefs = [hero]
bust sheet default; optional full-body turnaround
3. Environment plate generate_image — empty set, locked camera/light
4. Scene placement generate_image: env plate + sheet (+ optional wardrobe)
5. Fidelity close-up optional generate_image or capture_frame from the scene still
Do not skip to scene placement without an approved sheet. Reroll stills until lighting and identity pass.
Session gates
get_timeline→canGeneratelist_models({ type: "image" })- Propose each paid generation; wait for confirmation
- Folders e.g.
Character/Hero,Character/Sheets,Character/Scenes
Model picks
Confirm via list_models:
| Step | Prefer |
|---|---|
| Hero / sheet / env / scene | grok-imagine, gpt-image-2, or seedream-v5-pro (photoreal trio) |
Prefer gpt-image-2 / seedream-v5-pro for any step that needs referenceMediaRefs if the current Grok build rejects refs. Trust each model's aspect/resolution enums from list_models.
Step 1 — Hero still
Clear identity plate. Prefer candid editorial over beauty-retouch.
Include: age/skin/hair/eyes/expression; simple stable wardrobe; repeatable light; skin texture preserved (pores — no smoothing).
Avoid: unrepeatable glam grade; extreme pose that fights the sheet; busy BG that leaks into identity.
If the user supplies a photo, import_media and skip generation.
Step 2 — Character sheet
generate_image with referenceMediaRefs: [heroMediaRef].
Head / bust sheet (default — identity lock)
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.
- 2mo ago First seen · 136 lines · 104 tokens per session scan A 41851000b41a
character-pipeline is a skill published in the GitHub repository palmier-io/palmier-skills (83 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,414 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
character-pipeline compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| character-pipelinepalmier-io/palmier-skills | Skill | 83 | 2mo ago | Apache-2.0 | A | 104 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |