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 iii-hq/iii --skill presentationgit clone --depth 1 https://github.com/iii-hq/iiiWrote 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/iii-hq/iii/presentation)<a href="https://agentmods.dev/skills/iii-hq/iii/presentation"><img src="https://agentmods.dev/badge/skills/iii-hq/iii/presentation/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/iii-hq/iii/presentation"><img src="https://agentmods.dev/badge/skills/iii-hq/iii/presentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00051 | $0.04316 |
| Opus 5.5 | $0.00020 | $0.01726 |
| Sonnet 5.5 | $0.00010 | $0.00863 |
| Haiku 4.5 | $0.00005 | $0.00432 |
Grade A, and why
presentation 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- base/_viewer/index.html 1.0 KB
- base/_viewer/src/main.tsx 251 B
- base/_viewer/src/ViewerApp.tsx 3.6 KB
- base/.gitignore 51 B
- base/build.mjs 8.0 KB runs code
- base/COMPONENTS.md 15 KB
- base/index.html 1006 B
- base/package.json 753 B
- base/README.md 5.5 KB
- base/scripts/manifest.mjs 9.7 KB runs code
- base/src/components/diagrams/CliPlayground.tsx 5.3 KB
- base/src/components/diagrams/DurabilityTimeline.tsx 6.2 KB
- base/src/components/diagrams/EventFanOut.tsx 6.3 KB
- base/src/components/diagrams/FanOut.tsx 8.6 KB
- base/src/components/diagrams/Funnel.tsx 9.1 KB
- base/src/components/diagrams/SequencePlayer.tsx 7.3 KB
- base/src/components/diagrams/SpawnTree.tsx 9.8 KB
- base/src/components/diagrams/StepReveal.tsx 6.6 KB
- base/src/components/diagrams/SystemMap.tsx 14 KB
- base/src/components/Footer.tsx 1.4 KB
- base/src/components/PageShell.tsx 2.1 KB
- base/src/components/PlayerControls.tsx 1.3 KB
- base/src/components/schematic/Button.tsx 1.5 KB
- base/src/components/schematic/Caret.tsx 252 B
- base/src/components/schematic/Cell.tsx 638 B
- base/src/components/schematic/CodeBlock.tsx 1.7 KB
- base/src/components/schematic/FnChip.tsx 1.0 KB
- base/src/components/schematic/ModeToggle.tsx 1.1 KB
- base/src/components/schematic/Prompt.tsx 441 B
- base/src/components/schematic/Sheet.tsx 363 B
- base/src/components/schematic/StatusDot.tsx 675 B
- base/src/components/schematic/StatusPanel.tsx 1.4 KB
- base/src/components/schematic/Terminal.tsx 1.2 KB
- base/src/components/schematic/Wordmark.tsx 618 B
- base/src/components/schematic/WorkerCard.tsx 1.4 KB
- base/src/components/Section.tsx 2.1 KB
- base/src/components/SpecSheet.tsx 2.4 KB
- base/src/components/TopNav.tsx 3.2 KB
- base/src/content/highlight.tsx 8.6 KB
- base/src/content/markdown.tsx 9.4 KB
- base/src/content/mermaid.tsx 3.4 KB
- base/src/gallery/App.tsx 2.4 KB
- base/src/gallery/Gallery.tsx 2.7 KB
- base/src/gallery/main.tsx 229 B
- base/src/gallery/PresentationCard.tsx 2.6 KB
- base/src/gallery/site.ts 906 B runs code
- base/src/gallery/SiteFooter.tsx 656 B
- base/src/gallery/SiteHeader.tsx 1.2 KB
- base/src/hooks/useHashRoute.ts 1.5 KB runs code
- base/src/hooks/useStepper.ts 1.9 KB runs code
- base/src/hooks/useTheme.ts 694 B runs code
- base/src/index.css 4.9 KB
- base/src/lib/deck-types.ts 927 B runs code
- base/src/lib/utils.ts 166 B runs code
- base/src/pages/SpecPage.tsx 3.5 KB
- base/src/vite-env.d.ts 558 B runs code
- base/tsconfig.app.json 698 B
- base/tsconfig.json 107 B
- base/tsconfig.node.json 549 B
- base/vite.config.ts 1.0 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.
- 1mo ago First seen · 314 lines · 51 tokens per session scan A 16916565b2b0
presentation is a skill published in the GitHub repository iii-hq/iii (18,851 stars, last pushed today), with no licence file. It adds 51 tokens to every session and 4,316 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.
Other skills, from other repositories
composio
Build AI agents and apps with Composio - access 200+ external tools with Tool Router or direct execution.
a0-development
Develop or operate Agent Zero: projects, chats, tasks, framework, tools and API/WebUI.
azure-openai
Azure OpenAI provides the same models as OpenAI (GPT-4) but within the Azure compliance boundary, utilizing Active Directory and custom domain endpoints.
bullmq
Skill "bullmq" from ashish7802/awesome-api-skills, covering bullmq skill, ecosystem graph preview, recommended next skills, quick start and production patterns.
clerk
Clerk provides comprehensive authentication UIs and a powerful backend API. Install the specific SDK for your framework (e.g., @clerk/nextjs).
convex
Convex manages your database, server functions, and client state. You write server functions in TypeScript, and Convex automatically syncs the results to your React frontend via WebSockets.