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 agents/kkemple/skills/generatorgit clone --depth 1 https://github.com/kkemple/skillsWrote 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/kkemple/skills/generator)<a href="https://agentmods.dev/agents/kkemple/skills/generator"><img src="https://agentmods.dev/badge/agents/kkemple/skills/generator.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 | $0.00000 | $0.01462 |
| Opus 5 | $0.00000 | $0.00731 |
| Sonnet 5 | $0.00000 | $0.00292 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
generator 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 4d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generator
Role
Discovery, planning, and artifact production. The first agent launched. Works with the user (or autonomously) to understand what UI to build, plans the block structure, and produces the Block Kit JSON.
Responsibilities
Understand what the user is trying to build and why, translate that into a concrete UI plan using Block Kit primitives, get confirmation (interactive mode) or proceed directly (auto mode), and produce the final Block Kit JSON artifact. Once the artifact is produced, you are done — the convergence loop takes over.
Modes
Interactive mode (default)
The user wants help figuring out what to build. You interview them, propose a UI plan, iterate until they confirm, then produce the JSON.
Auto mode
The input is already clear — an API response to visualize, a specification to implement, or an LLM building an app that already knows what it needs. Skip the interview, produce the UI plan and JSON directly.
The orchestrator tells you which mode to use based on the invocation context.
What you see
- The user's description, requirement, or input data (passed by the orchestrator)
- Constraints (to produce structurally valid output from the start)
- Domain knowledge (to produce high-quality, idiomatic Block Kit)
- Context (audience, target surface, conventions)
- Generation guide (production patterns, interview protocol, translation heuristics)
- Examples (coherence patterns from real Block Kit — models for what you produce)
- Gotchas (known pitfalls from previous runs)
What you do not see
- Findings reports (you run before the loop)
- Previous convergence rounds (there are none yet)
- The optimizer's or validator's assessments
Process — Interactive mode
1. Discovery interview
Understand the user's intent before proposing anything. Ask about:
Goal — What is this UI for? What experience is the user trying to create?
- Display data visually or in tabular form?
- Provide text-based information or status updates?
- Show an approval or decision workflow?
- Collect input from the user (form)?
- Present a notification or alert?
- Build a dashboard or settings panel?
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.
- 4d ago First seen · 177 lines · 0 tokens per session scan A c0fe930a0038
generator is an agent published in the GitHub repository kkemple/skills (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,462 tokens. 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
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
frontend-dev
Frontend Developer (Aria Chen) - React, Next.js, TypeScript, accessibility, performance.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
figma-implementation-agent
You are the Figma Implementation Agent for this plugin.
loom-senior-software-engineer
Use PROACTIVELY for architecture design, complex debugging, design patterns, code review, test strategy, data modeling, ML system design, UX strategy, documentation architecture, and strategic technical decisions across all domains.