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 0xagi-bsky-social/Codex-Skills --skill cinematic-storyboard-sheetgit clone --depth 1 https://github.com/0xagi-bsky-social/Codex-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/0xagi-bsky-social/codex-skills/cinematic-storyboard-sheet)<a href="https://agentmods.dev/skills/0xagi-bsky-social/codex-skills/cinematic-storyboard-sheet"><img src="https://agentmods.dev/badge/skills/0xagi-bsky-social/codex-skills/cinematic-storyboard-sheet/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/0xagi-bsky-social/codex-skills/cinematic-storyboard-sheet"><img src="https://agentmods.dev/badge/skills/0xagi-bsky-social/codex-skills/cinematic-storyboard-sheet.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00110 | $0.01157 |
| Opus 5 | $0.00055 | $0.00579 |
| Sonnet 5 | $0.00022 | $0.00231 |
| Haiku 4.5 | $0.00011 | $0.00116 |
Grade A, and why
cinematic-storyboard-sheet 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 12d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic Storyboard Sheet
Overview
Create a polished vertical storyboard sheet image as a continuous top-to-bottom cinematic timeline. This skill is image-only: when it is invoked, call image_gen with the completed prompt and do not return a text prompt, plan, explanation, markdown sheet, or any non-image artifact.
Prioritize production-design clarity: widescreen frame thumbnails, precise shot metadata, bordered text blocks, restrained black-and-grey styling, and no calendar dates anywhere in the rendered sheet.
Output Contract
- Always use the
image_gentool to generate the final storyboard sheet image. - Do not use file generation, SVG/HTML composition, plain text, or prompt-only output as the final result.
- Do not ask clarifying questions before generation; make reasonable cinematic assumptions from the provided storyboard text and character references.
- If the user provides incomplete storyboard text, generate a professional storyboard sheet image with inferred shot details or clearly designed placeholder shot rows.
- If
image_genis not available in the current environment, do not substitute another output format.
Workflow
- Parse the user's storyboard text into frames, preserving shot order.
- Extract or infer for each frame: timestamp/timecode, shot number, shot title, action, camera/lens/movement, lighting/color, and dialogue if present.
- Use referenced character images as identity and costume references when available; preserve distinguishing features consistently across frames.
- Compose one complete
image_genprompt that includes the full layout specification and all parsed frame content. - Run the quality gate below against the prompt before generation.
- Call
image_genimmediately with that prompt as the final action.
Layout Specification
- Format: one continuous vertical sheet, read top to bottom as a timeline.
- Background: pure black only.
- Typography: light grey text, clean production-board hierarchy, high legibility, no decorative clutter.
- Frame area: left column contains cinematic frames in a strict 3:2 aspect ratio.
- Text area: right column aligns side-by-side with its corresponding frame.
- Frame metadata: each frame must clearly show
Timestamp,Shot Number, andShot Title. - Timestamp meaning: use only story timecode or relative shot timing supplied by the user. Do not render calendar dates, years, month names, day names, or production-date stamps.
- Required text blocks: include bordered sections labeled exactly
Action,Camera / Lens / Movement, andLighting / Color. - Dialogue rule: if spoken lines exist, add a separate bordered
Dialoguesection immediately next to theActionsection. If no spoken lines exist, omitDialogueentirely. - Borders: use thin light-grey borders around every required text block and optional dialogue block.
- Continuity: align each text cluster to the vertical center/top rhythm of its corresponding frame; avoid orphaned labels, floating text, or mismatched frame descriptions.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 88 lines · 110 tokens per session scan A 921a11d92319
cinematic-storyboard-sheet is a skill published in the GitHub repository 0xagi-bsky-social/Codex-Skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 110 tokens to every session and 1,157 once invoked, about $0.0006 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 skills, from other repositories
prewalk
Use when the user wants a coding task executed with a strong planner model first and a faster/cheaper executor model after the first successful implementation edit.
insights
Answer questions about the user's own Claude Code usage history — sessions, hours, streaks, error rate, burnout risk, cost/cache savings, most-used tools, and git commit activity — using the locally installed cc-atlas CLI. Use whenever the user asks about their Claude Code usage, productivity, burnout, streaks, cost…
menu
Point the user to cc-atlas's full interactive menu (dashboard, project comparison, session replay, team activity, anomalies, goals) — screens that need a real terminal.
export
Export cc-atlas's computed stats as Prometheus metrics or a JSON summary.
report
Generate a Claude Code usage report for a period (day, week, or month).
sync
Ingest the latest Claude Code session transcripts and configured git history into cc-atlas's local database.