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/vibenpx skills add harshii0509/designStack --skill vibegit 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 | $0.00053 | $0.02302 |
| Opus 5 | $0.00026 | $0.01151 |
| Sonnet 5 | $0.00011 | $0.00460 |
| Haiku 4.5 | $0.00005 | $0.00230 |
Grade A, and why
ds-vibe 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble
"../lib/env.sh" "vibe"
What this skill does
You describe the feeling you want — in plain English, no design knowledge needed. I'll give you three completely different visual directions to compare. You pick one, and I'll set up your design rules to match that direction so everything you build from now on follows the same aesthetic.
This reads your existing Design Bible first, so I'm suggesting evolution — not replacement.
This skill chooses direction. If the user already knows the direction and wants to audit a screen, route them to /ds-look.
Step 1 — Read the existing Design Bible (if it exists)
If DESIGN_BIBLE is yes, follow the standard extraction protocol in lib/bible-reader.md. Note:
- Current vibe words (The feeling section)
- Current colors (L1)
- Current fonts (L1)
- Recent Memory Log entries
- What's already been built and confirmed as intentional
This context prevents suggesting something that would discard all existing confirmed design decisions. Frame the directions as evolutions of what's there.
If DESIGN_BIBLE is no:
"I don't have your design rules yet — I'll create three directions from scratch. After you pick one, I'll set up your Design Bible so everything stays consistent going forward."
Step 2 — Understand what they want
Ask the user:
"How do you want your product to feel? You can describe it in any of these ways:
- Feeling words: 'calm and focused', 'bold and energetic', 'warm and friendly', 'minimal and clean'
- A reference: 'like Notion', 'like Stripe but warmer', 'like Duolingo without the green'
- A contrast: 'the opposite of what I have now — it feels too corporate'
- A person: 'like a really good doctor's office — trustworthy but not cold'
- Anything: just describe it however makes sense to you"
Wait for their response. If they give very sparse input (e.g. just "modern"), follow up once:
"Got it — anything else? Are you thinking more minimal/clean, or more bold/expressive? Light or dark?"
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 · 222 lines · 53 tokens per session scan A fd279288f101
ds-vibe is a skill published in the GitHub repository harshii0509/designStack (13 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 2,302 once invoked, about $0.0003 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…