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 Yuuhann1999/codex-storyboard --skill process-storyboard-tasksgit clone --depth 1 https://github.com/Yuuhann1999/codex-storyboardWrote 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/yuuhann1999/codex-storyboard/process-storyboard-tasks)<a href="https://agentmods.dev/skills/yuuhann1999/codex-storyboard/process-storyboard-tasks"><img src="https://agentmods.dev/badge/skills/yuuhann1999/codex-storyboard/process-storyboard-tasks/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/yuuhann1999/codex-storyboard/process-storyboard-tasks"><img src="https://agentmods.dev/badge/skills/yuuhann1999/codex-storyboard/process-storyboard-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 31 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.02132 |
| Opus 5.5 | $0.00024 | $0.00853 |
| Sonnet 5.5 | $0.00012 | $0.00426 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
process-storyboard-tasks 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 1mo 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process Codex Storyboard Tasks
Task recovery
While processing a long render, call heartbeat_storyboard_generation_task
at least every 10 minutes. Tasks expire after 30 minutes without a heartbeat.
If the user released a task or its ID changed, stop attempting to complete it;
never attach a late output to a replacement task automatically.
Process the local storyboard queue. The MCP tools start the bundled local app automatically when needed and default to http://127.0.0.1:43218.
If the current Codex session does not expose Storyboard MCP tools such as list_storyboard_generation_tasks, claim_storyboard_generation_task, or complete_storyboard_generation_task, first use tool_search to search for codex storyboard and load the deferred tools. Only if tool_search is unavailable or cannot find them, tell the user to start a new Codex conversation or restart Codex so plugin tools are reloaded.
Mandatory B-roll motion gate
For every B-ROLL shot routed to hyperframes or remotion, plan_broll_motion is mandatory. Do not claim the task, write a composition, download media, render, or complete the task before this gate is confirmed. The MCP server rejects both claim and completion when the confirmed plan is missing.
Reuse-first template policy (mandatory)
Treat the local template roots and the two required repositories as the primary production library. Before designing a new composition, identify a concrete reusable template, component, shot skeleton, GIF/MP4, or other directly usable media candidate from the inspected sources. If a source has no suitable candidate, record that explicit empty result and the reason. Select the closest existing candidate, reuse it directly whenever it fits, and make only the minimum changes needed for the shot's dialogue, visual hierarchy, palette, typography, and duration.
Do not start from a blank composition when an existing candidate can carry the shot's core semantic structure. If no candidate fits, adapt the closest existing skeleton and record the original path plus the mismatch and adaptation boundary. A from-scratch motion system is an exception: use it only after the plan records the local roots and both repositories searched, the concrete mismatch, why adaptation would fail, and the smallest new structure required. The confirmed plan must carry this evidence in selectedTemplate, motionSkeleton, sources, and researchNotes.
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.
- 1mo ago Changed · +8 lines 499024eecf05
- 1mo ago Changed · +22 lines e6e5e355b19d
- 2mo ago First seen · 68 lines · 60 tokens per session scan A 7cafe01abddd
process-storyboard-tasks is a skill published in the GitHub repository Yuuhann1999/codex-storyboard (347 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 2,132 once invoked, about $0.0002 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.
process-storyboard-tasks compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| process-storyboard-tasksYuuhann1999/codex-storyboard | Skill | 347 | 1mo ago | MIT | A | 60 | Claude Code, Codex |
| video-prompt-engineerArch-Dog/video-prompt-engineer | Skill | 24 | 3mo ago | MIT | A | 126 | Codex |
| storyboard-designerGenNiao-Photograph/storyboard-designer | Skill | 4 | 18d ago | none | A | 129 | Codex |
| video-storyboard-genanyhui/video-storyboard-gen-skill | Skill | 27 | 3mo ago | none | A | 118 | Claude Code, Codex |
| expense-review-policyopenai/openai-cookbook | Skill | 77k | yesterday | MIT | A | 17 | Claude Code, Codex |
| skill-creatorzhayujie/CowAgent | Skill | 48k | yesterday | MIT | A | 61 | Claude Code, Codex |
| new-appEigenwise/atomic-agents | Skill | 6.3k | 8d ago | MIT | A | 76 | Claude Code |