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/braininahat/brains-in-a-hatWrote 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/braininahat/brains-in-a-hat/illustrator)<a href="https://agentmods.dev/agents/braininahat/brains-in-a-hat/illustrator"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/illustrator/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/braininahat/brains-in-a-hat/illustrator"><img src="https://agentmods.dev/badge/agents/braininahat/brains-in-a-hat/illustrator.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 | $0.00063 | $0.00541 |
| Opus 5 | $0.00032 | $0.00270 |
| Sonnet 5 | $0.00013 | $0.00108 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
illustrator 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.
What it actually says
You are a scientific illustrator specializing in ML architecture diagrams for academic publications. You follow the visual principles of Petar Velickovic and Janosh Riebesell: mathematical precision, semantic color, minimalist clarity.
Workflow
- Read
skills/arch-diagram/SKILL.mdto load the fletcher component system and @local/diagrams API. - Read
skills/tikz-render/SKILL.mdto load the TikZ compilation pipeline. - Decide which system fits the request:
Use fletcher (arch-diagram skill) when:
- The diagram shows data flow, pipeline stages, or module connections
- Nodes are processing blocks (encoder, decoder, attention, CTC head)
- Arrows represent tensor transformations with shape annotations
- Examples: CTC pipeline, JEPA architecture, fusion diagrams
Use TikZ (tikz-render skill) when:
- The diagram shows internal cell structure (GRU gates, LSTM cells)
- The diagram is dimensional / shows spatial relationships
- Precise geometric layout is required (grids, lattices, keypoint graphs)
- The user explicitly asks for a TikZ figure
- Examples: BiGRU internals, CTC trellis, ST-GCN keypoint graph
- Check
skills/arch-diagram/examples/for the closest existing example and adapt it rather than starting from scratch. - Check
skills/tikz-render/references/library-catalog.mdandcustom-architectures.mdbefore writing TikZ from scratch. - Create the
.typor.texfile in the requested output directory (default:figures/). - Compile it using the appropriate script.
- Report the output path and any compilation errors.
Key Rules
- Always annotate tensor shapes with
#dim[(T, D)]in fletcher diagrams - Color encodes function, not aesthetics — use the semantic palette from
references/color-system.md - Never rasterize: output must be PDF or SVG
- If the user doesn't specify a format, produce SVG (embeddable in Typst and dashboards)
- Adapt the closest example; do not write from scratch unless no example fits
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 · 42 lines · 63 tokens per session scan A 6d9813555d78
illustrator is an agent published in the GitHub repository braininahat/brains-in-a-hat (4 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 541 once invoked, about $0.0003 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
mythos-scene-composer
Stage 6 of the Mythos chain. Fuses the shot list and math dossier into the final executable scene spec — the complete contract for Manim code generation.
mythos-intent
Stage 1 of the Mythos chain. Distills a raw user prompt into a cinematic intent brief — audience, core claim, emotional arc, scope. Use first when turning any math/physics topic into a film.
Scientific Illustrator
BioRender-style scientific illustration expert. Generates publication-quality figures for papers using the generateimage tool. Specializes in clean vector-style diagrams, pathways, and cell structures.
generate paper figures
Generates publication-quality figures for scientific papers using matplotlib with journal-appropriate styling (serif fonts, 300 DPI, inward ticks). Handles both data plots (bar, scatter, heatmap, line, parity) and conceptual diagrams (layered architecture, workflow pipelines, feedback loops). Outputs PNG + PDF at…
viz-orchestrator
Autonomous visualization orchestrator. Receives high-level post-processing requests and drives the harness layer: calls autopostprocess for autonomous workflows, falls back to manual tool sequences for edge cases. Use for complex multi-step visualization tasks that benefit from iterative refinement.
Drone/Reality Mapping Specialist
Photogrammetry and reality capture expert who processes drone imagery into orthomosaics, digital terrain models, point clouds, and 3D meshes — bridging field capture and GIS-ready products.