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-compose)<a href="https://agentmods.dev/skills/cogni-work/insight-wave/design-compose"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/design-compose/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-compose"><img src="https://agentmods.dev/badge/skills/cogni-work/insight-wave/design-compose.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 | $0.00194 | $0.02609 |
| Opus 5.5 | $0.00078 | $0.01044 |
| Sonnet 5.5 | $0.00039 | $0.00522 |
| Haiku 4.5 | $0.00019 | $0.00261 |
Grade A, and why
design-compose 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Compose
Bind a normalized brief to the pattern library and hand on a target-neutral semantic-composition@2. The validator is the authority: never alter, shorten, merge or reorder content to make a composition pass — frozen copy, unit order and source lineage are exactly what it protects. When no accepted pattern fits a unit, report that to the author and stop.
Inputs
- A normalized brief — the
dataof a successfulpublishing-validatenormalizerun, saved as its own JSON file. Pass the artifact itself, not the envelope around it. - A design-system pin —
{name, version}and nothing else. The name is thetheme_slugfrom themanage-themesselection handoff. The version is the cogni-publishingversionin.claude-plugin/plugin.jsonfor a bundled theme, since bundled themes are versioned with the plugin, or the revision the user supplies for a user theme — ask when there is none. Never use the theme manifest'sschema_version. The pin is recorded as data; the composition resolves no token. - The requested targets —
html,pptx, or both. Every unit's pattern must support every requested target.
Workflow
- Run
check-patternsto confirm the library is valid and to see which patterns are accepted. - Read
${CLAUDE_PLUGIN_ROOT}/references/design-composition.mdfor each pattern's eligibility, slots, limits and variants, and for the binding rules. - Group consecutive frozen records into units, up to the chosen pattern's
constraints.max_records, and choose one accepted pattern and variant per unit — by slidetypeor section role, record kind and whether the records carry data. One exception: on a unit that declares metric intent whose bound text repeats one of the brief's key figures, leave both out and letcomposeroute it (step 5). Routing declines in three cases — no matching figure, a single match in a unit of more than four bound texts, or a candidate whose limits the draft's bindings exceed — and a unit it declines stays patternless and is rejected asunknown-pattern, so give such a unit a pattern instead. Parallel direct sections can share one comparison unit. A narrativevisual_intentis a hint the choice may decline, never a requirement. A brief that carries sources needs onesourcesunit: the narrative source-register slide takes it, and a direct brief ends on asourcesunit with no bindings. - Write a draft that binds content by reference only:
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 · -2 tokens per session a51be9462387
- 1mo ago First seen · 96 lines · 196 tokens per session scan A 8908fd73262c
design-compose is a skill published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 194 tokens to every session and 2,609 once invoked, about $0.0008 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 2026-09-14.
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.