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.
git clone --depth 1 https://github.com/fatihkan/badiWrote 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/agents/fatihkan/badi/tasarim-kurator)<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.
<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>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 | $0.00042 | $0.00923 |
| Opus 5 | $0.00021 | $0.00462 |
| Sonnet 5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00092 |
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.
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:
-
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
-
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
-
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
-
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 mandatory — colors.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
...
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.
- 9d ago First seen · 100 lines · 42 tokens per session scan A 5d00ac9d298e
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.
Other agents, from other repositories
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
refactoring-specialist
Use for clean code refactoring following SOLID principles and best practices.
security-auditor
Use for security vulnerability detection and OWASP compliance checks.
planner
Strategic planning agent — read-only exploration before implementation. Use to decompose tasks, analyze codebases, and produce a detailed plan. Never modifies files.