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 antropos17/Aegis --skill design-systemgit clone --depth 1 https://github.com/antropos17/AegisWrote 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/antropos17/aegis/design-system)<a href="https://agentmods.dev/skills/antropos17/aegis/design-system"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/design-system/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/antropos17/aegis/design-system"><img src="https://agentmods.dev/badge/skills/antropos17/aegis/design-system.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 | $0.00027 | $0.00446 |
| Opus 5.5 | $0.00011 | $0.00178 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
design-system 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AEGIS interface design
Select the reference for this task
For implementation, locate frontend/observatory/DESIGN.md, reference/README.md and the preserved reference/ artwork in the selected checkout. Read the current entrypoint and stylesheet imports. If these files are absent, inspect git worktree list and the project handoff before choosing a source; do not silently switch to a historical temporary checkout.
DESIGN.md indexes the current contract and relevant dated amendments in DESIGN-HISTORY.md. Apply later decisions to the same property; the compact-density amendment supersedes the earlier panel inset. The approved Observatory reference is the integration baseline. Old Shield/Fancy mockups and historical plans do not override it. A running implementation is not proof of visual approval.
For an explicit redesign, logo/icon exploration or prototype request, follow the new brief and use the existing design as context. Alternative shapes, colors and layouts are allowed within that brief. Keep concept assets separate from application integration until the user requests that integration. Static concept work does not require running Electron or the full repository test suite.
Implement and verify
When integrating real data, preserve the approved composition, stylesheet order, typography, spacing, artwork and controls except where the requested change calls for a revision. Use the selected implementation's semantic tokens; do not assume an older tokens.css or font list defines Observatory.
Preserve meaningful absence and stale states, stamped process identities, and pending/failure feedback. A disabled action explains the actual capability limit. Use original local artwork for existing third-party agent identities.
Visually check affected states against the applicable reference at matching viewport, theme and scale. For interface changes, cover the relevant light/dark, focus, selection and empty/error states; check reduced motion when motion changes. Select viewport and scale cases from the current design contract and affected workflow; distinguish the fixed application layout from supported OS/accessibility zoom.
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 · 25 lines · 27 tokens per session scan A bba0253a26d0
design-system is a skill published in the GitHub repository antropos17/Aegis (157 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 446 once invoked, about $0.0001 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 2026-10-17.
Other skills, from other repositories
create-canvas
Create a project Copilot extension canvas for the current workspace.
winui-design
Read before writing or changing WinUI 3 XAML: choosing controls, pages and navigation, layout, Fluent Design, theming, accessibility, x:Bind, real samples, and checking that APIs exist with winapp find-api. Not for WPF or WinForms UI, even if the app uses the Windows App SDK.
openscreen-design
Use this skill to generate well-branded interfaces and assets for OpenScreen (an AI-native screen-recording studio & video editor), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
before-after
Produce a before/after visual comparison of an evlog surface (landing, docs, telemetry, playgrounds) and share it as public Blob URLs. Load when a change is visual, when someone asks for screenshots or a visual diff, or when a shipped PR touches apps/docs or apps/telemetry and deserves visual evidence.
eac-desktop-tips
A quick reference for using and troubleshooting features in the Deepseek Harness EAC desktop client. It covers window behavior, conversation rollback, plugins, desktop pets, Skills, MCP services, updates, and logs.
cyrene-diagram
A design guide for making static SVG learning cards: small diagrams or reference cards rendered as images. It explains when to use a card instead of Mermaid, a text-based diagram format, and sets layout, color, size, and safety rules.