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 instructions/harshii0509/designstack/claude-mdgit 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 | $0.00894 | $0.00894 |
| Opus 5 | $0.00447 | $0.00447 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
designStack CLAUDE.md 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
designStack
Designer-first Claude Code skills for designers building their own products. Speak plain English, show screenshots when available, save constantly.
Skill routing
When the user's request matches one of these, invoke the skill FIRST — before answering directly.
| When the user says... | Invoke |
|---|---|
| "something broke", "it's not working", "I'm stuck", "fix this error", error message in chat | dstack:unstuck |
| "does this screen look right", "check this page after my UI change", "visual QA on this screen", "look at this page" | dstack:look |
| "check on mobile", "does this work on phone", "responsive" | dstack:mobile |
| "check accessibility", "a11y", "can everyone use this" | dstack:a11y |
| "save my progress", "checkpoint", "commit this" | dstack:save |
| "share this", "deploy", "get a link", "show someone", "go live" | dstack:share |
| "update designStack", "upgrade designStack", "new version of designStack" | dstack:upgrade |
| "set the vibe", "aesthetic direction", "pick a visual direction", "style guide" | dstack:vibe |
| "scan the whole site for drift", "brand check across pages", "check consistency sitewide" | dstack:brand |
| "polish this before launch", "final check before sharing", "release gate" | dstack:polish |
| "add animation", "make interactions feel less static", "make it move" | dstack:animate |
| "add delight", "improve the success state", "improve the empty state" | dstack:delight |
| "set up design rules", "build design bible", "capture my brand", first-time setup | dstack:context |
Available designStack skills
/ds-context— Build the Design Bible (run once per project)/ds-unstuck— Diagnose errors visually/ds-look— Visual QA against design rules/ds-mobile— Responsive check (3 breakpoints)/ds-a11y— Accessibility audit with letter grade/ds-save— Git checkpoint with human-readable message/ds-share— Deploy and get a shareable link/ds-upgradeor/ds-update— Pull the latest designStack release/ds-vibe— Set aesthetic direction from feeling words/ds-brand— Brand consistency scan/ds-polish— Pre-ship quality check (11 dimensions)/ds-animate— Add purposeful motion/ds-delight— Add joy moments
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.
- 2d ago First seen · 69 lines · 894 tokens per session scan A 8191c97b5849
designStack CLAUDE.md is an instructions file published in the GitHub repository harshii0509/designStack (13 stars, last pushed 3mo ago), licensed MIT. It adds 894 tokens to every session, about $0.0045 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.