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 nexu-io/codex-slides --skill codex-slides-browsergit 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-browser)<a href="https://agentmods.dev/skills/nexu-io/codex-slides/codex-slides-browser"><img src="https://agentmods.dev/badge/skills/nexu-io/codex-slides/codex-slides-browser/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/nexu-io/codex-slides/codex-slides-browser"><img src="https://agentmods.dev/badge/skills/nexu-io/codex-slides/codex-slides-browser.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 Excessive Agency · line 19 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00072 | $0.00603 |
| Opus 5.5 | $0.00029 | $0.00241 |
| Sonnet 5.5 | $0.00014 | $0.00121 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
codex-slides-browser 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.
What it actually says
Codex Slides Browser
This specialized skill remains for compatibility. The canonical
codex-slides sibling skill owns the full workflow and portable CLI.
- Call
open_codex_slideswhen the MCP tool is available. Otherwise runnode ../codex-slides/scripts/codex-slides.mjs open --json '<input>'from this skill directory. PassprojectIdwhen the user named a deck; otherwise omit it for the create workspace. Useview:"scenarios"for the 24-workflow catalog,view:"design-files"plusprojectIdand optionalfilePathfor project files, orview:"brand-system"plusprojectIdfor the brand editor. - Navigate the returned resource link in the Codex in-editor Browser. Do not
stop after printing the URL and do not ask the user to open it manually.
Follow
browserHandoff.urlexactly so slide, panel, version, mode, checkpoint, conversation, and run focus are preserved. - For a new deck, always open and verify the home/create screen before any
research, outline, or rendering call. Submit the topic in that UI so it
creates a durable project and opens the guided workspace. Use
start_project/ CLIstart-projectonly if UI submission needs a deterministic fallback, then navigate its project resource immediately. - Keep the Browser visible and operate the checkpoints in order: clarify, outline review, inspiration/style selection, render, deck review. Do not run the entire workflow invisibly in the Codex conversation.
- Use direct MCP tools or the canonical skill CLI for deterministic recovery and mutations, then reload or inspect the Browser result.
- Verify the visible outcome before reporting completion.
Long Deck Agent, outline, and render operations can continue after navigation.
Use start_project_run, retain its runId, and use get_project_run,
wait_project_run, or cancel_project_run without closing the Browser.
Use the Browser for scenario/slot selection, @ Design File references, brand
system editing, Play from the current slide or the beginning, dual-window
presenter mode, speaker notes editing/AI generation, slide navigation, direct on-canvas
marking, layout inspection, and other visual interactions. If the Browser
capability is unavailable in the current Codex surface, return the resource
link and explain that limitation rather than claiming it opened.
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.
- 1mo ago First seen · 44 lines · 72 tokens per session scan A 87cc5df4eaf9
codex-slides-browser is a skill published in the GitHub repository nexu-io/codex-slides (951 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 603 once invoked, about $0.0003 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.
Other skills, from other repositories
gpt-image2-ppt
A tool for creating presentation slides as high-resolution images and packaging them into a 16:9 PowerPoint file. It turns a Markdown outline or slide plan into a styled deck using OpenAI image generation.
high-quality-slides
A method for creating polished presentation slides, including HTML slide decks, with research, a clear story, chosen visuals, and fixed layouts.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
stss
Reduce defensive disclaimers, stacked hedging, and self-protective narration when drafting, rewriting, or auditing proposals, articles, case studies, captions, and other reader-facing prose. Use when defensive wording is requested for review or appears in a draft, including wording the assistant adds. Preserve…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.