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/alwkala/tidyfactor-design/agents-mdgit clone --depth 1 https://github.com/alwkala/tidyfactor-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/alwkala/tidyfactor-design/agents-md)<a href="https://agentmods.dev/instructions/alwkala/tidyfactor-design/agents-md"><img src="https://agentmods.dev/badge/instructions/alwkala/tidyfactor-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 | $0.01894 | $0.01894 |
| Opus 5 | $0.00947 | $0.00947 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
tidyfactor-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 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — TidyFactor Design System & Full UI Design Lifecycle Engine
Build interactive, code-native HTML/CSS/JS design prototypes (Figma alternative) with strict structural visual consistency across all pages. Zero per-page CSS/JS, zero inline <style> or <script> tags, zero build step. Every visual and interaction decision is made once and lives in design-system/.
🛠️ CLI Execution Modes (Human Terminal Wizard vs AI Agent Non-Interactive)
- Human Terminal Interactive Mode (
npx @alwkala/tidyfactor-design): Launches step-by-step interactive CLI wizard (readline) prompting human developers in terminal for target directory, CSS foundation, visual school, and optional brand image color extraction. - AI Agent Non-Interactive Mode (
npx @alwkala/tidyfactor-design -yor--foundation=... --school=...): AI Agents bypass interactive terminal prompts by passing non-interactive flags (-y/--yes) or settingAGENT_MODE=1orCI=1.
⚡ Skill & 24 Modular Slash Commands (7 Lifecycle Stages)
This project exposes an Agentic Skill under .agents/skills/tidyfactor-design/SKILL.md (and .claude-skill/SKILL.md). The following 24 slash commands covering all 7 stages of the UI Design Lifecycle are supported:
| Stage | Command | Purpose | Reference Spec |
|---|---|---|---|
| 1. Discovery | study |
Extract Design DNA (colors, typography, macrostructure) from reference URL/image | .agents/skills/tidyfactor-design/references/commands/study.md |
| 1. Discovery | brief |
Establish 3-Question Design Context Brief & Fit Test | .agents/skills/tidyfactor-design/references/commands/brief.md |
| 2. Foundation | init |
Primary deliverable — scaffold design system, tokens, foundation, base components & initial page | .agents/skills/tidyfactor-design/references/commands/init.md |
| 2. Foundation | brand |
Scaffold, extract, or migrate brand.json v2 schema |
.agents/skills/tidyfactor-design/references/commands/brand.md |
| 2. Foundation | typography |
Select mood-routed font pairing (7 Arabic + Latin routes) | .agents/skills/tidyfactor-design/references/commands/typography.md |
| 2. Foundation | school |
Select and document design-movement direction (Minimalist, Brutalism, Glassmorphism, Neumorphism, Swiss, Luxury) | .agents/skills/tidyfactor-design/references/commands/school.md |
| 2. Foundation | tokens |
Read/scaffold design-system/tokens.css & brand.json single source of truth |
.agents/skills/tidyfactor-design/references/commands/tokens.md |
| 2. Foundation | palette |
Extract color palette & WCAG 2.1 AA contrast scores via extract_palette.py |
.agents/skills/tidyfactor-design/references/commands/palette.md |
| 2. Foundation | assets |
Asset hygiene, web compression & Python image tools | .agents/skills/tidyfactor-design/references/commands/assets.md |
| 3. Architecture | layout |
Select surface layout archetype (fullbleed, editorial, spatial, interface, minimal, product, store, auto) |
.agents/skills/tidyfactor-design/references/commands/layout.md |
| 3. Architecture | nav-footer |
Choose Navigation (N1-N9) and Footer (Ft1-Ft8) archetypes | .agents/skills/tidyfactor-design/references/commands/nav-footer.md |
| 3. Architecture | page |
Add a new marketing or content page (markup-only, zero page-specific CSS/JS) | .agents/skills/tidyfactor-design/references/commands/page.md |
| 3. Architecture | dashboard |
Add a new app or dashboard screen with data surfaces and shell layouts | .agents/skills/tidyfactor-design/references/commands/dashboard.md |
| 4. Components | components |
Build reusable component library in design-system/components.css with 8-state wrappers |
.agents/skills/tidyfactor-design/references/commands/components.md |
| 4. Components | states |
Define component interactive states (hover, active, focus, disabled, loading, empty, error, success) | .agents/skills/tidyfactor-design/references/commands/states.md |
| 5. Motion | motion |
Motion tokens, micro-interactions, ambient layers, scroll-film & z-stack layers in motion.js |
.agents/skills/tidyfactor-design/references/commands/motion.md |
| 5. Motion | flow |
Wire clickable prototype navigation toolbar (proto-nav.js) between screens |
.agents/skills/tidyfactor-design/references/commands/flow.md |
| 5. Motion | i18n |
Arabic/English RTL support, modesty rules & identity typography (El Messiri/Tajawal, never Amiri above 24px) | .agents/skills/tidyfactor-design/references/commands/i18n.md |
| 6. Quality | perf |
Verify numeric asset performance budgets (hero ≤ 400KB, logo ≤ 40KB, fonts ≤ 3 families / 4 weights) | .agents/skills/tidyfactor-design/references/commands/perf.md |
| 6. Quality | audit |
Comprehensive quality-bar & design consistency audit report | .agents/skills/tidyfactor-design/references/commands/audit.md |
| 6. Quality | clone |
Convert mode — extract design tokens & computed styles from reference site | .agents/skills/tidyfactor-design/references/commands/clone.md |
| 6. Quality | retrofit |
Improve mode — unify a drifted multi-page prototype into a single design system | .agents/skills/tidyfactor-design/references/commands/retrofit.md |
| 7. Delivery | handoff |
Export developer handoff specs, token map, and component state matrix | .agents/skills/tidyfactor-design/references/commands/handoff.md |
| 7. Delivery | deploy |
Preview server, static asset packaging & prototype presentation export | .agents/skills/tidyfactor-design/references/commands/deploy.md |
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 · 76 lines · 1,894 tokens per session scan A 2fc5e99cb8b4
tidyfactor-design AGENTS.md is an instructions file published in the GitHub repository alwkala/tidyfactor-design (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,894 tokens to every session, about $0.0095 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
deepsteve CLAUDE.md
Claude Code instructions for deepsteve/deepsteve, covering deepsteve, development workflow, restart the daemon after making changes, check if running, and read logs and stop the daemon.
deepsteve AGENTS.md
AGENTS.md instructions for deepsteve/deepsteve, covering agents.md - agent guidelines for deepsteve, project overview, running the application, development and production.
coograph styling.instructions.md
Conventions for CSS/styling files — loaded only when editing styles.
pixcode AGENTS.md
AGENTS.md instructions for alicomert/pixcode, covering agents.md, commands, smoke tests (manual, no npm script), architecture boundaries and agent adapters.
ux-audit AGENTS.md
Instructions for narenkatakam/ux-audit, covering ux audit — agent instructions, scope, repository goals, content rules and ux rules to preserve.
Warden-AI AGENTS.md
AGENTS.md instructions for rynald0cst0ltziam/Warden-AI, covering agents.md — warden, what this is, build / test / verify commands, architecture (where things live) and non-negotiable rules.