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 agentmods add skills/harshii0509/designstack/brandnpx skills add harshii0509/designStack --skill brandgit clone --depth 1 https://github.com/harshii0509/designStackWhat 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 | $0.00049 | $0.01945 |
| Opus 5 | $0.00024 | $0.00972 |
| Sonnet 5 | $0.00010 | $0.00389 |
| Haiku 4.5 | $0.00005 | $0.00194 |
Grade A, and why
ds-brand 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 3d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
"../lib/env.sh" "brand"
What this skill does
Check if everything still looks like it belongs to the same product. As you build over time, small things drift — a button becomes the wrong shade, a font switches, padding gets inconsistent. This scan catches all of that and shows you exactly where, so you can decide what to fix.
This is the multi-page consistency scan. If the user only cares about one screen after a recent UI change, route them to /ds-look. If they want a final launch gate, route them to /ds-polish.
Requires a Design Bible. If none exists, run /ds-context first.
Step 1 — Check for Design Bible
If DESIGN_BIBLE is yes, follow the standard extraction protocol in lib/bible-reader.md when reading the Bible.
If DESIGN_BIBLE is no:
"I need your Design Bible to run a brand check — it's the set of rules I compare everything against. You haven't set one up for this project yet.
Run
/ds-contextfirst — it takes about 5 minutes to set up. After that,/ds-brandwill know exactly what to look for."
Stop here if no Bible.
If DESIGN_BIBLE is yes, read the full Bible. Extract every rule:
- L1: exact hex values for all colors, exact font families, spacing scale, radius values
- L4: component-level rules (button colors, card styles, nav style)
- Memory Log: note any recent intentional changes so you don't flag them as drift
Step 2 — Get the pages to check
Ask the user:
"Which pages should I check? I can: A) Check 3–5 pages you tell me (recommended) B) Check everything I can find (most thorough — might take a while)
What's your URL? (e.g.
http://localhost:3000)"
If they say B, discover pages by:
$B goto <base URL>
$B links
Collect up to 8 unique internal URLs to check.
If they only want one page, tell them:
"For a single page after a recent UI change,
/ds-lookis the better fit./ds-brandis for a multi-page consistency scan." Then ask them for at least 3 pages or suggest switching to/ds-look.
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.
- 3d ago First seen · 208 lines · 49 tokens per session scan A 1a61ac7f9eed
ds-brand is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,945 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…