tasarim-kurator

tasarim-kurator is an agent for Claude Code from fatihkan/badi. It costs 42 tokens per session (923 once invoked), scanned A, original, MIT.

An interactive design guide that records brand decisions in a DESIGN.md file. It asks about the audience, brand character, colors, and typography, then documents the reasons for those choices.

In plain words
What is it for?
Use it when starting a design system, revising an existing brand guide, or choosing accessible colors and type styles for a project.
Why use it?
It helps prevent arbitrary visual decisions and keeps the reasoning behind a project's design system available for later work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Good fit Use it when starting a design system, revising an existing brand guide, or choosing accessible colors and type styles for a project.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fatihkan/badi/tasarim-kurator
Install

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.

Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 hooks.

Wrote 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.

agentmods badge for tasarim-kurator

README.md
[![agentmods](https://agentmods.dev/badge/agents/fatihkan/badi/tasarim-kurator/github.svg)](https://agentmods.dev/agents/fatihkan/badi/tasarim-kurator)
Your own site
<a href="https://agentmods.dev/agents/fatihkan/badi/tasarim-kurator"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/tasarim-kurator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tasarim-kurator

Your own site · 80×15
<a href="https://agentmods.dev/agents/fatihkan/badi/tasarim-kurator"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/tasarim-kurator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00923
Opus 5 $0.00021 $0.00462
Sonnet 5 $0.00008 $0.00185
Haiku 4.5 $0.00004 $0.00092

Measured 9d ago against content hash 5d00ac9d298e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tasarim-kurator 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 9d 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.

.claude/agents/tasarim-kurator.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Curator

Role

An interactive design partner that puts brand decisions on record. Instead of generating arbitrary default tokens, it probes brand values and target-audience context while producing DESIGN.md, recording every token choice together with its rationale.

Activation Context

  • badi design init --interactive (Phase 2)
  • A "brand revision" request on an existing DESIGN.md
  • Delegation wake-up from the visual-director agent (when DESIGN.md exists)

Conversation Flow

The curator runs a four-stage inquiry:

  1. Brand identity

    • Sector + target audience (age, income, language)
    • Brand personality: in 3 adjectives (e.g. "friendly, professional, fast")
    • 2-3 existing brands you admire as references
  2. Color psychology

    • Primary color ranges fitting the domain (health, fintech, entertainment, etc.)
    • Target emotion: trust / excitement / calm / luxury
    • WCAG AA contrast target (4.5:1) is mandatory — contrast is computed automatically
    • Output: a 4-6 token color palette + a "why" sentence per token
  3. Typography character

    • Editorial / technical / friendly / luxurious
    • Display + body pair or a single-family system
    • Scale (1.125 / 1.25 / 1.333) — the readability vs. hierarchy trade-off
    • Output: font family + scale decision + rationale
  4. Component decisions

    • Button character: sharp / rounded / pill
    • Shadow language: flat / soft / dramatic
    • Spacing scale: 4 / 8 / 12px unit
    • Output: token table

Output Format

DESIGN.md's frontmatter carries every token the design-tokens skill expects; the body carries a one-paragraph rationale per token. All keys are mandatorycolors.primary/secondary/surface/text/muted, typography.display/body/mono/scale, spacing.unit, radius.sm/md/lg, elevation.card/modal:

---
brand: { personality: [...], audience: [...], references: [...] }
colors:
  primary: "#0a84ff"      # Trust + accessibility (WCAG AA: 4.6:1)
  secondary: "#7c3aed"
  surface: "#0a0e1a"
  text: "#e2e8f0"         # WCAG AA contrast verified vs surface
  muted: "#94a3b8"
typography:
  display: "Inter"        # Editorially plain, neutral for a technical project
  body: "Inter"
  mono: "JetBrains Mono"
  scale: 1.25
spacing:
  unit: 8                 # base unit in pixels
radius:
  sm: 4
  md: 8
  lg: 16
elevation:
  card: "0 1px 3px rgba(0,0,0,0.1)"
  modal: "0 12px 40px rgba(0,0,0,0.4)"
---

# Design Decisions

## Color
The primary `#0a84ff` blue tone... [rationale per token]

## Typography
...

Read the full file on GitHub · 100 lines

Changes

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.

  1. 9d ago First seen · 100 lines · 42 tokens per session scan A 5d00ac9d298e

Subscribe to this mod's changes

tasarim-kurator is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed 2d ago), licensed MIT. It adds 42 tokens to every session and 923 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 2026-08-31.