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 skills/nexu-io/codex-slides/codex-slides-decknpx skills add nexu-io/codex-slides --skill codex-slides-deckgit clone --depth 1 https://github.com/nexu-io/codex-slidesWrote 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/nexu-io/codex-slides/codex-slides-deck)<a href="https://agentmods.dev/skills/nexu-io/codex-slides/codex-slides-deck"><img src="https://agentmods.dev/badge/skills/nexu-io/codex-slides/codex-slides-deck.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 | $0.00076 | $0.00902 |
| Opus 5 | $0.00038 | $0.00451 |
| Sonnet 5 | $0.00015 | $0.00180 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
codex-slides-deck 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 5d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Slides Deck
The canonical codex-slides sibling skill owns the complete workflow. Use the
codex_slides MCP tools when available; otherwise run its self-contained CLI
at ../codex-slides/scripts/codex-slides.mjs. Keep the live workspace available
in the in-editor Browser whenever visual review helps.
Choose the flow
-
Default to the live Browser workflow: open the Codex Slides home screen, submit the request there, then operate the created project through clarify, outline confirmation, style selection, rendering, and review. Keep the Browser visible throughout.
-
If Browser UI submission fails, use
start_project/ CLIstart-projectto create the durable project shell, immediately open its returned URL, and continue in the UI. -
Use
list_scenarios/ CLIscenarioswhen a named workflow such as business report, document-to-deck, data insights, brand application, localization, or batch generation fits. Upload required slot files and passscenarioId,materialIds, andmaterialContextsinto creation. -
Only when the user explicitly requests an unattended/headless one-call result, call
create_deckor CLI commandcreate. -
For CLI automation or recovery, call
create_outline, optionallyrevise_outlineandrank_inspiration, thenrender_deck; the CLI commands areoutline,revise-outline,inspiration, andrender. -
For an existing deck, use
list_projectsorget_project, then choose the smallest mutation tool.
Edit with the right tool
- Use
edit_deckfor natural-language add/rewrite/redraw/optimize requests. - Use
manage_slidefor deterministic add, duplicate, delete, or transition. - Use
regenerate_slidefor one slide. - Use
restyle_deckfor a whole-deck template/style change. - Use
upload_materialbefore creation, editing, or restyling when a local reference file matters. - Use
upload_slide_imagefor a finished PNG. - Use
mark_edit_slidewhen the user supplies an annotated PNG and wants a clean revised slide. - Use
get_speaker_notes,update_speaker_notes, andgenerate_speaker_notes(CLIspeaker-noteswithget,set, orgenerate) for presenter-only talk tracks. These notes persist per slide, appear in the speaker window, and are embedded in PPTX export. - Use
list_design_files,read_design_file,write_design_file, andupload_design_filefor the project file workspace. Pass selected paths asdesignFilePathswhen revising an outline or editing a deck. - Use
get_brand_design_systemthenupdate_brand_design_systemfor persistent project-wide brand/style rules. Redraw only when requested. - Use
start_project_runfor navigation-independent chat, outline, or render work; retain the returnedrunIdand track or cancel it explicitly.
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.
- 5d ago First seen · 72 lines · 76 tokens per session scan A 95ad5ce7ff68
codex-slides-deck is a skill published in the GitHub repository nexu-io/codex-slides (859 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 902 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
high-quality-slides
Use this skill when the user asks for a "high-quality" / "professional" / "Genspark-style" / "投资人级别" / "演示级" deck, or when they reference Genspark, Gamma, beautiful HTML slides, or pixel-perfect presentations. Trigger on requests like "做一份PPT", "生成幻灯片", "pitch deck", "做汇报", or when the user uploads research material…
oh-my-ppt-layout
Must be read before creating, relaying out, or repairing Oh My PPT slide layouts. Defines the per-page decision path, the named layout pattern catalog, canvas budgeting, collision avoidance, chart overpack guardrails, and title readability rules.
vertical-3-4-layout-skill
Must be read before creating, relaying out, or repairing 3:4 vertical Oh My PPT pages. Defines poster-card layout, focal hierarchy, vertical section planning, evidence grouping, compact two-column pockets, chart/list budgeting, plus catalog and checklist references for 1200x1600 canvases.
children-warm-orange
采用儿童节童趣绘本风,整体以暖橙渐变打底,搭配明亮的草绿和粉嫩点缀色,营造活泼、可爱、充满节日欢乐的视觉氛围——像幼儿园六一联欢会海报那种热热闹闹、甜甜暖暖的感觉。它跟"夏日晴朗蓝绿"的区别在于:橙是主调,蓝退到点缀位,整体更"暖"更"甜",是儿童节的专属气质。.
hand-drawn-autumn
这是一本被秋风吹开的旅行手账——色调是晾在窗台的南瓜与枫叶,笔触是孩童第一次出游时小心翼翼的描线。整体气质温暖、松弛、带一点天真,像把一段山野漫步的回忆随手贴进了本子里。阅读它的人应该闻得到纸张味,而不是屏幕味。.
palace-ink-red
整体采用沉稳的新中式高级感视觉:像故宫宫墙在傍晚光线里的深红,搭配玄石般的深灰与宣纸米色,气质克制、厚重、安静,但标题要有强烈存在感。画面不要做得花哨,而是用大色块、粗字体、圆角分区和极少量装饰,把"东方审美里的力量感"表达出来。.