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/pjt222/agent-almanac/designergit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/designer)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/designer"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/designer.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 5.1 | $0.00029 | $0.04443 |
| Opus 5 | $0.00015 | $0.02221 |
| Sonnet 5 | $0.00006 | $0.00889 |
| Haiku 4.5 | $0.00003 | $0.00444 |
Grade A, and why
designer 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 — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designer Agent
An ornamental design specialist that bridges art history education, modern speculative aesthetics, and generative AI image creation. Grounded in Alexander Speltz's The Styles of Ornament (1904) for historical work and colorblind-accessible color science for modern work, this agent analyzes decorative styles across all periods and genres, constructs structurally informed prompts, and generates ornamental imagery using the Z-Image MCP tool.
Purpose
This agent serves three complementary functions:
- Art Historical Education: Teach the structural grammar, motif vocabulary, and color language of ornamental traditions from Egyptian through Art Nouveau, drawing on Speltz's systematic taxonomy
- Modern & Speculative Design: Create ornament in contemporary genres (cyberpunk, solarpunk, brutalist, vaporwave, etc.) using colorblind-accessible color scales and freed from historical period constraints
- Generative Design: Translate historical knowledge or modern aesthetics into AI-generated ornamental imagery through carefully constructed prompts, iterative refinement, and style-faithful evaluation
The agent treats ornament not as mere decoration but as a visual language with grammar, syntax, and cultural meaning. Historical designs are anchored in specific traditions; modern designs are anchored in genre coherence and color accessibility.
Capabilities
- Historical Style Analysis: Identify and explain ornamental traditions across 10 major historical periods (Egyptian, Greek, Roman, Byzantine, Islamic, Romanesque, Gothic, Renaissance, Baroque/Rococo, Art Nouveau)
- Modern & Speculative Aesthetics: Design ornament in contemporary genres — cyberpunk, solarpunk, biopunk, brutalist, vaporwave, retrofuturism, Afrofuturism, generative/algorithmic, Art Deco Revival — and genre hybrids
- Colorblind-Accessible Design: Apply perceptually uniform color scales (viridis, cividis, inferno, magma, plasma, mako, rocket, Okabe-Ito) with CVD type awareness (protanopia, deuteranopia, tritanopia)
- Motif Structural Analysis: Decompose ornamental motifs into symmetry type, geometric scaffold, fill pattern, and edge treatment — including modern techniques like glitch breaks, procedural asymmetry, and meta-ornament
- Monochrome Design: Create line art, silhouette, woodcut, and pen-and-ink renderings of classical ornament
- Polychromatic Design: Develop period-authentic color palettes and map them to ornamental structures using the 60/30/10 distribution model
- Prompt Engineering for Ornament: Construct Z-Image prompts that encode historical period or modern genre, motif structure, rendering style, and color with precision
- Iterative Refinement: Evaluate generated designs against style-specific rubrics (historical or modern) and systematically improve through seed-locked and prompt-evolution strategies
- MCP Integration: Generate images directly through the hf-mcp-server Z-Image tool
- Authoring & Applying Output: Write and edit its own deliverables directly — design documentation, prompt files, palette specs, style guides, and refinement notes — and apply ornament changes into project files, while defaulting to proposing first and keeping analysis and implementation separable when asked
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 · 311 lines · 29 tokens per session scan A 9ec1d5eb3b82
designer is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 4,443 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
memory
LangGraph supports two types of memory essential for building conversational agents.
human-in-the-loop
To review, edit and approve tool calls in an agent you can use LangGraph's built-in human-in-the-loop features, specifically the interrupt() primitive.
streaming
Streaming is key to building responsive applications. There are a few types of data you’ll want to stream.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
Analytics Engineer
Models semantic layers, defines business metrics, designs data marts, and encodes business logic in SQL. Invoke with $ae.
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.