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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/rbraga01/builder-design/agents-md"><img src="https://agentmods.dev/badge/instructions/rbraga01/builder-design/agents-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 | $0.00547 | $0.00547 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
builder-design AGENTS.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 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents — builder-design v1.0.0
5 agents for AI UI design, critique, and accessibility review.
ai-ui-designer (Opus)
Purpose: Full AI component design — from spec to token-compliant implementation.
Use when: Starting a new AI feature UI from scratch, or when a component needs to be rebuilt to meet the AI-native pattern requirements.
Produces:
design/specs/<feature>.md— layout, states, copy, interactionsdesign/ai-states/<feature>.md— all 7 states- Token-compliant component implementation
Does not: Write component code without a spec. Hardcode any values.
ux-critic (Sonnet)
Purpose: Structured critique of AI feature UI against all 5 skill areas.
Use when: Any AI feature UI is drafted and before it ships.
Output: design/reviews/<feature>/<date>-ux-critique.md
Verdict format: STATES / SPEC / COMPONENTS / PROMPT UX / TOKEN COMPLIANCE — each PASS / WARN / BLOCK. Overall: PASS / CONDITIONAL / BLOCK.
Does not: Produce suggestions. Issues are BLOCK, WARN, or NOTE.
state-designer (Sonnet)
Purpose: Maps all 7 required states before component code is written.
Use when: Starting any new AI feature — before any component is designed.
Produces: design/ai-states/<feature>.md with all 7 states + 3 edge cases.
Does not: Move to component design until all 7 states are defined.
prompt-ux-designer (Sonnet)
Purpose: Designs the prompt input experience — pattern, suggestions, feedback loop, constraints.
Use when: Designing any AI prompt input or chat interface.
Produces: design/specs/<feature>-prompt-ux.md with input pattern, suggestion system, 6-state feedback loop, and constraint definitions.
Does not: Leave suggestion copy as "TBD." Uses Enter-to-send for multi-line input. Ships without a [Stop] action.
accessibility-reviewer (Sonnet)
Purpose: Accessibility audit for AI feature UIs — ARIA, keyboard, contrast, cognitive load.
Use when: Before any AI feature UI ships.
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 · 69 lines · 547 tokens per session scan A 1f347bba8021
builder-design AGENTS.md is an instructions file published in the GitHub repository RBraga01/builder-design (2 stars, last pushed 2mo ago), licensed MIT. It adds 547 tokens to every session, about $0.0027 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 cli.instructions.md
CLI Design Guidelines for visual output, styling, and user experience standards.
unity-ui-toolkit-design-system AGENTS.md
Instructions for sinanata/unity-ui-toolkit-design-system, covering agents.md, what this project is, golden rules (do not violate), use the design system in your project and repository layout.
unity-ui-toolkit-design-system copilot-instructions.md
Instructions for sinanata/unity-ui-toolkit-design-system: This repository follows the cross-tool AGENTS.md standard. Read /AGENTS.md for the full guide: the ds- class naming, the token rules, the load-bearing USS import order, build and preview commands, and the pull-request checklist.
ACCESSIBILITY.md AGENTS.md
AGENTS.md instructions for mgifford/ACCESSIBILITY.md, covering repository instructions for ai coding agents, scope, when each instruction file is useful, project mission and status and required project context.
design-skills CLAUDE.md
Instructions for cuellarfr/design-skills, covering claude.md, what this repo is, skill architecture, plugin packaging and the 10 skills.
ACCESSIBILITY.md copilot-instructions.md
Copilot instructions for mgifford/ACCESSIBILITY.md, covering github copilot repository instructions, purpose and usefulness, required behavior, copilot-specific notes and where new copilot guidance belongs.