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/rbraga01/builder-design/claude-mdgit clone --depth 1 https://github.com/RBraga01/builder-designWrote 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/instructions/rbraga01/builder-design/claude-md)<a href="https://agentmods.dev/instructions/rbraga01/builder-design/claude-md"><img src="https://agentmods.dev/badge/instructions/rbraga01/builder-design/claude-md.svg" alt="Measured on agentmods" 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 | $0.00556 | $0.00556 |
| Opus 5 | $0.00278 | $0.00278 |
| Sonnet 5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
builder-design 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 5d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
builder-design — AI UI Design Skills Pack v1.0.0
What This Pack Is
8 skills and 5 agents that enforce design quality for AI feature UIs. Every skill has a Completion Statement Format — a literal code block that must be filled with real values before work is considered done.
Skills
| Skill | Trigger |
|---|---|
ai-states-required |
Before any AI feature component code is written |
design-before-code |
Before any component implementation begins |
accessible-ai-output |
Before any AI output rendering ships |
ai-component-patterns |
When implementing any of the 6 AI-native components |
prompt-ux-design |
Before designing any AI prompt input |
ai-output-design |
When designing AI response rendering |
ai-onboarding-design |
When designing first-run or empty state for an AI feature |
design-token-audit |
Before merging any AI feature UI component |
Agents
| Agent | Model | Use When |
|---|---|---|
ai-ui-designer |
Opus | Designing a new AI component from scratch |
ux-critic |
Sonnet | Reviewing any AI feature UI before ship |
state-designer |
Sonnet | Mapping states for a new AI feature |
prompt-ux-designer |
Sonnet | Designing the prompt input experience |
accessibility-reviewer |
Sonnet | Accessibility audit before ship |
Enforcement Model
Every skill's Completion Statement Format must be filled with real values:
- Real component names
- Real file paths
- Real counts (not "all states designed" — "7/7 states designed")
- Real verdicts (PASS / BLOCK — not "looks good")
File Conventions
- State maps:
design/ai-states/<feature>.md - Component specs:
design/specs/<feature>.md - Prompt UX specs:
design/specs/<feature>-prompt-ux.md - UX critiques:
design/reviews/<feature>/<date>-ux-critique.md - Accessibility reviews:
design/reviews/<feature>/<date>-accessibility.md
Quality Bar
A component is not complete until:
- Spec exists at
design/specs/<feature>.md - State map exists at
design/ai-states/<feature>.md - All AI-native component patterns satisfied
- Zero hardcoded values (design-token-audit passes)
- Accessibility review: no BLOCK issues
- UX critique: no BLOCK issues
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.
- 5d ago First seen · 59 lines · 556 tokens per session scan A 3634f207966e
builder-design CLAUDE.md is an instructions file published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 556 tokens to every session, about $0.0028 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 2026-08-31.
Other instructions, from other repositories
apm python.instructions.md
Python development guidelines.
starwind-ui AGENTS.md
AGENTS.md instructions for starwind-ui/starwind-ui, covering agents.md, project shape, useful commands and contribution conventions.
Codex-Skills AGENTS.md
AGENTS.md instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
barkeep AGENTS.md
AGENTS.md instructions for iannuttall/barkeep, covering agent notes, product rules, repo map, commands and app structure.
OpenGUI CLAUDE.md
Claude Code instructions for Core-Mate/OpenGUI, covering opengui release - repository guide for claude code / codex, 1. repository positioning, 2. default working rules, 3. high-level architecture and 4. directory map.
ng-blatui AGENTS.md
AGENTS.md instructions for anousss007/ng-blatui, covering ng-blatui — agent guide, use the official angular tooling, hard rules (this repo), commands and after changing a component's public api.