Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-publishingWrote 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/cogni-work/insight-wave/design-render)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/design-render"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/design-render/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/cogni-work/insight-wave/design-render"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/design-render.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 | $0.00176 | $0.02601 |
| Opus 5.5 | $0.00070 | $0.01040 |
| Sonnet 5.5 | $0.00035 | $0.00520 |
| Haiku 4.5 | $0.00018 | $0.00260 |
Grade A, and why
design-render 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Render
Turn a validated semantic-composition@2 into a client-grade deliverable and hand back its files. The platform route delegates PPTX creation to the host presentation skill; HTML follows this plugin's DOM contract. On every route, design-verify independently gates handover. Never edit a rendered page, deck or composition to make a check pass: frozen copy, unit order and source lineage are exactly what they protect.
Every delivery contains the native artifact, platform provenance, independent verification and visual review.
Inputs
- A normalized brief — the
dataof a successfulpublishing-validatenormalizerun, saved as its own JSON file. - A semantic composition — the
dataof a successfuldesign-composecomposerun whosetargetsinclude the target to render. - A theme — the
theme_pathfrom themanage-themesselection handoff, or a theme directory. Its directory name must equal the composition'sdesign_system.name, and it must ship the authoritativetokens/*.jsoncarrying the token roles listed in${CLAUDE_PLUGIN_ROOT}/references/design-render.md; the pptx target also needs its colour tokens in hex. Every bundled theme qualifies; a tier-0 theme (theme.mdonly) derives its tokens throughmanage-themesOperation 7. A theme may also ship licensed faces, one per weight of a family, declared in itsassets/fonts/faces.jsonbeside each face's licence; the html target embeds every face of the copy family, each under its declared weight (declaration fields:design-render.md§Fonts). The bundledcogni-worktheme ships DM Sans Regular and Bold. - The language — taken from the brief's metadata; pass
--languagefor a direct brief that does not state one (for example--language de). - The narrative — optional context only. Never use it as a source of deliverable copy.
Platform route — PPTX
Resolve the host presentation skill
Resolve by host, in this order. On Codex, select the bundled presentations:Presentations skill even when document-skills:pptx is installed. On an Anthropic host, select its installed anthropic-skills:pptx or document-skills:pptx capability. On another host, select an installed skill whose description explicitly claims .pptx creation. Rely on the host's normal description-based skill triggering; do not create or consult a renderer registry. Load the selected theme as the design system. Its token files under tokens/, their compiled tokens.resolved.json when present, assets/fonts/faces.json when shipped, and theme.md are authoritative when another brand skill disagrees. Resolve semantic dark-surface roles to existing theme colors: use explicit bg-dark / text-on-dark tokens when present; otherwise map them to the theme's existing primary / bg colors and record that mapping in provenance and visual review. Invent no color.
What ships with it
2 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.
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 Changed · +7 lines · +29 tokens per session 5fc739664421
- 1mo ago Changed · -8 lines · +147 tokens per session 89c245cfd0ce
- 1mo ago First seen · 94 lines · 0 tokens per session scan A 32328c69379d
design-render is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 176 tokens to every session and 2,601 once invoked, about $0.0007 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 2026-09-15.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.