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-known-errorsnpx skills add nexu-io/codex-slides --skill codex-slides-known-errorsgit 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-known-errors)<a href="https://agentmods.dev/skills/nexu-io/codex-slides/codex-slides-known-errors"><img src="https://agentmods.dev/badge/skills/nexu-io/codex-slides/codex-slides-known-errors.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 | $0.00067 | $0.00630 |
| Opus 5 | $0.00034 | $0.00315 |
| Sonnet 5 | $0.00013 | $0.00126 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
codex-slides-known-errors 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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Slides Known Errors
Classify the failure before retrying. Preserve the same project id and run id; do not recreate a deck merely because a Browser tab closed or a wait timed out.
Runtime and installation
- Plugin version contract fails:
.codex-plugin/plugin.jsonmust start with the exact rootpackage.jsonversion plus+codex.. The desktop package must use the same product version. - App is unreachable: inspect
CODEX_SLIDES_URLandCODEX_SLIDES_LOG. The local MCP launcher may need to prepare dependencies or a standalone build. - Installed skill or tool inventory looks stale: reinstall/upgrade the plugin and start a new Codex task so the versioned plugin cache is refreshed.
Durable runs
- Another run is active: inspect it with
get_project_run. Wait, cancel it explicitly, or allow a Deck Agent request to remain in the visible queue. - Wait timed out: the run was not cancelled. Continue with
wait_project_runor reopen itsbrowserHandoff. - Run id is missing after completion: this indicates an old runtime without
terminal
runHistory; refresh the plugin/runtime before retrying the task. - Run is stopping: do not start a conflicting render. Poll until it becomes
cancelled, then continue.
Browser handoff and project resume
- Use the exact returned
browserHandoff.url; do not reconstruct a project URL. - Keep all focus parameters:
slide,panel,version,mode,checkpoint,conversation, andrun. - A clarify/research project may route through
/?resume=<id>. The continuation query must survive that redirect. - Presenter mode needs a user gesture for its second window. A presenter deep link opens the Play menu at the correct slide instead of bypassing popup protection.
Rendering and project state
- A partially rendered or paused deck is resumable. Read the project and start
a durable
renderrun for the existing project. - If Codex state and Browser state differ, read
/runs/get_projectas the canonical snapshot, then reload the same Browser handoff. - Do not report success for slides whose status is
erroror whose persisted image cannot be loaded.
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.
- 4d ago First seen · 58 lines · 67 tokens per session scan A 9914adcac0d8
codex-slides-known-errors is a skill published in the GitHub repository nexu-io/codex-slides (859 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 630 once invoked, about $0.0003 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
gpt-image2-ppt
Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/ /STYLEID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用…
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-chart
Must be read before adding or modifying Oh My PPT slide charts. Defines product-safe Chart.js usage, canvas layout constraints, axis label rules, and retry fixes.
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.
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.