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 larsboes/Axon --skill slide-deckgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/slide-deck)<a href="https://agentmods.dev/skills/larsboes/axon/slide-deck"><img src="https://agentmods.dev/badge/skills/larsboes/axon/slide-deck/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/larsboes/axon/slide-deck"><img src="https://agentmods.dev/badge/skills/larsboes/axon/slide-deck.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 | $0.00185 | $0.03261 |
| Opus 5 | $0.00093 | $0.01631 |
| Sonnet 5 | $0.00037 | $0.00652 |
| Haiku 4.5 | $0.00018 | $0.00326 |
Grade A, and why
slide-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 today.
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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slide deck
A deck states an argument with pictures. This skill gives you the mechanism and the judgment. The mechanism is a theme, layout archetypes, a deterministic build, a render pass and a rehearsal pass. The judgment is what each slide owes the next one, and what an academic talk is judged on.
All content lives in the user's own deck directory. This skill holds mechanism only.
The tool surface is <skill>/scripts/deck build|check|render|readiness|timing|handout|themes|init.
Python runs through uv. The launcher pins the dependencies.
How this skill works with the others
Four skills share this ground. Each one owns a different thing, and the boundaries are worth stating.
| skill | owns |
|---|---|
academic-writing |
The argument in the paper or thesis, and the constructs a talk must render: contribution types, the validity taxonomy, the citation discipline. |
human-writing |
The prose a person reads. Notes, README text and any explanatory writing in the deck should pass its scanner. |
asd-ste100 |
Text that a machine parses without a person to resolve ambiguity. Error messages, tool descriptions, and the instruction files of this skill. |
unslop |
Source code and web interfaces. |
diagrams |
A Mermaid source and the figure it renders to. It derives the renderer theme from this skill's theme.json, so a diagram cannot land in a deck in different colours. |
| this skill | The deck module, the theme, the layout, the speaker notes and the rehearsal passes. |
Two consequences follow.
The instruction files in this skill follow the asd-ste100 structural rules, because an
agent parses them. The sentences are short and active, each sentence carries one
instruction, and the files use no semicolons.
The talk's own words belong to the user. When a deck reads as machine-written, hand the
notes and the slide text to human-writing. When the argument is unclear, hand the
source document to academic-writing. This skill does not rewrite the user's argument.
What ships with it
33 files 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.
- assets/deck.template.py 4.9 KB runs code
- assets/themes/slate.json 710 B
- assets/themes/warm-scientific-teal.json 729 B
- evals/evals.json 9.2 KB
- references/academic-narrative.md 7.2 KB
- references/academic-register.md 4.6 KB
- references/citing-on-slides.md 3.1 KB
- references/defence-readiness.md 4.6 KB
- references/design-system.md 9.4 KB
- references/evidence-on-slides.md 3.9 KB
- references/genre-academic-job-talk.md 3.3 KB
- references/genre-dsr-defence.md 6.8 KB
- references/genre-empirical-cs-talk.md 3.4 KB
- references/gotchas.md 4.8 KB
- references/narrative.md 8.7 KB
- references/slide-recipes.md 15 KB
- references/theming.md 6.2 KB
- references/verification.md 6.3 KB
- scripts/deck 1.5 KB
- scripts/deckkit/__init__.py 1.2 KB runs code
- scripts/deckkit/__main__.py 159 B runs code
- scripts/deckkit/check.py 13 KB runs code
- scripts/deckkit/cli.py 11 KB runs code
- scripts/deckkit/deck.py 15 KB runs code
- scripts/deckkit/errors.py 354 B runs code
- scripts/deckkit/handout.py 4.3 KB runs code
- scripts/deckkit/layout.py 19 KB runs code
- scripts/deckkit/markup.py 3.2 KB runs code
- scripts/deckkit/readiness.py 2.6 KB runs code
- scripts/deckkit/render.py 6.5 KB runs code
- scripts/deckkit/slide.py 15 KB runs code
- scripts/deckkit/theme.py 9.1 KB runs code
- scripts/deckkit/timing.py 6.3 KB runs code
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.
- today First seen · 267 lines · 185 tokens per session scan A 88ff8cea315d
slide-deck is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed yesterday), licensed MIT. It adds 185 tokens to every session and 3,261 once invoked, about $0.0009 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 2026-09-15.
Other skills, from other repositories
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
invoice
A printable invoice page — sender + recipient block, line items table, tax breakdown, totals, and payment instructions. Use when the brief mentions "invoice", "bill", "billing statement", or "发票".
data-report
Turns CSV, Excel, or JSON data into a polished visual report page.