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 caption-templatesgit 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/caption-templates)<a href="https://agentmods.dev/skills/palmier-io/palmier-skills/caption-templates"><img src="https://agentmods.dev/badge/skills/palmier-io/palmier-skills/caption-templates/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/caption-templates"><img src="https://agentmods.dev/badge/skills/palmier-io/palmier-skills/caption-templates.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 | $0.00130 | $0.06989 |
| Opus 5.5 | $0.00052 | $0.02796 |
| Sonnet 5.5 | $0.00026 | $0.01398 |
| Haiku 4.5 | $0.00013 | $0.00699 |
Grade A, and why
caption-templates 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 — 612 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Palmier Pro caption templates
Caption styling is where an agent most easily produces something ugly: it pairs a font with a size that doesn't suit it, picks a neon color that fights the footage, or stacks an outline + background + shadow that no editor would ship. This skill replaces that guesswork with a default. Every value below was read out of a real Palmier project and confirmed against rendered frames.
Hard rules
- Pick exactly one template. Paste its config verbatim. Do not blend two templates, do not "improve" a color, do not add an outline or background a template doesn't have.
- No style at all is a valid answer. If the user just says "add captions" with no aesthetic intent, call
add_captionswith nostyle/animation/transform— the app's own default is clean and correct. Reach for a template only when the user signals a look ("bold", "podcast", "TikTok", "make them pop", "match my brand", names a vibe). - Match orientation. Vertical templates are authored for 1080×1920, horizontal for 1920×1080. Using the wrong set gives text that is comically large or unreadably small — see Porting across canvas sizes.
- Fonts outside this catalog are fair game — but verify them. Palmier's font list is far larger than the 13 families used here; this catalog is a curated slice, not the available set. Set whatever font the user asks for. What doesn't change: after setting an unfamiliar font, render a frame with
inspect_timelineand confirm it actually resolved instead of silently falling back to a default. - Always verify. After
add_captionsorupdate_text, runinspect_timelineon a frame inside the caption range and actually look at it.
Workflow
- [ ] 1. get_timeline — canvas width/height, fps, which track has speech
- [ ] 2. Pick ONE template from the picker below (or none — see rule 2)
- [ ] 3. add_captions with that template's exact block
- [ ] 4. inspect_timeline mid-caption — confirm it renders as described
- [ ] 5. Report the template name you used
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 · 612 lines · 130 tokens per session scan A 885887ebf58c
caption-templates is a skill published in the GitHub repository palmier-io/palmier-skills (83 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 130 tokens to every session and 6,989 once invoked, about $0.0005 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 2026-08-30.
caption-templates compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| caption-templatespalmier-io/palmier-skills | Skill | 83 | 2mo ago | Apache-2.0 | A | 130 | 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 |