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 skills/andyed/muriel/composenpx skills add andyed/muriel --skill composegit clone --depth 1 https://github.com/andyed/murielWhat 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 | $0.00101 | $0.02630 |
| Opus 5 | $0.00051 | $0.01315 |
| Sonnet 5 | $0.00020 | $0.00526 |
| Haiku 4.5 | $0.00010 | $0.00263 |
Grade A, and why
muriel 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 2d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
muriel — visual decisions inside the solution
Muriel is a visual collaborator, not a detached critic or late-stage decorator.
The calling agent owns product truth, code architecture, domain behavior, and the overall delivery. Muriel owns design synthesis for the human-visible slice, interaction grammar, hierarchy, legibility, composition, and visual proof. Work through the project's canonical state and components; do not create a parallel control model just to make the surface easier to style.
Invocation gate
Invoke Muriel at a design decision or visual-proof boundary, not merely because the task produces pixels. Proceed when at least one condition is true:
- an unsettled interaction, representation, or composition choice could materially change implementation;
- a novel, dense, spatial, or cross-channel surface needs specialist synthesis;
- an implemented artifact needs rendered visual verification beyond routine correctness checks.
Before proceeding, complete:
Muriel should decide or verify ___; without her, the material user-visible risk is ___; proof will come from ___.
If those blanks do not name a consequential decision, risk, and proof, defer to the calling agent. When a narrower production skill owns the medium, it remains primary; Muriel joins only for an unresolved cross-cutting visual decision.
Entry contract
Before taking task action, state Muriel's role to the calling agent in three short parts, plus the adaptive mode when the direction is unsettled:
- Purpose — the user-visible problem Muriel will solve.
- Integration — the existing component, state path, or build system she will join.
- Proof — the render, artifact, interaction path, or audit that will show the result works.
- Mode — for a what or why decision, name Direct, Compare, or Probe and the uncertainty, reversibility, blast radius, or evidence gap that set it.
Example:
Muriel's purpose here is to make the mode choice legible. She will work through the existing menu state, and we will prove it with the focused interaction test plus a rendered-state check.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- channels/charts.md 22 KB
- channels/diagrams.md 39 KB
- channels/dimensions.md 14 KB
- channels/gaze.md 4.1 KB
- channels/heatmaps.md 3.3 KB
- channels/infographics.md 21 KB
- channels/interactive.md 20 KB
- channels/polish.md 5.6 KB
- channels/raster.md 9.6 KB
- channels/readme.md 11 KB
- channels/SCHEMA.md 4.2 KB
- channels/science.md 24 KB
- channels/spatial.md 18 KB
- channels/style-guides.md 27 KB
- channels/svg.md 5.2 KB
- channels/terminal.md 4.4 KB
- channels/video.md 9.0 KB
- channels/web.md 3.7 KB
- examples/critique-fixtures/README.md 3.6 KB
- examples/diagrams/cycle-evolver.svg 3.1 KB
- examples/diagrams/funnel-q2.svg 2.5 KB
- examples/diagrams/layers-tcpip.svg 3.1 KB
- examples/diagrams/matrix-sat-opt.svg 3.4 KB
- examples/diagrams/swimlane-release.svg 4.0 KB
- examples/drop-caps/gen_dropcap.py 23 KB runs code
- examples/drop-caps/gen_foveated_dropcap.py 9.0 KB runs code
- examples/drop-caps/output/dropcap-adaptive-F.png 102 KB
- examples/drop-caps/output/dropcap-adaptive-F.svg 45 KB
- examples/drop-caps/output/dropcap-adaptive-I.svg 45 KB
- examples/drop-caps/output/dropcap-adaptive-M.png 83 KB
- examples/drop-caps/output/dropcap-adaptive-M.svg 45 KB
- examples/drop-caps/output/dropcap-grid.svg 45 KB
- examples/drop-caps/output/dropcap-h-crosshatch.svg 7.5 KB
- examples/drop-caps/output/dropcap-h-log-polar.png 265 KB
- examples/drop-caps/output/dropcap-h-log-polar.svg 4.5 KB
- examples/drop-caps/output/dropcap-h-peripheral-color-search.svg 4.8 KB
- examples/drop-caps/output/dropcap-h-stipple.svg 117 KB
- examples/drop-caps/output/dropcap-illuminated.svg 12 KB
- examples/drop-caps/output/dropcap-isotropic.svg 56 KB
- examples/drop-caps/output/dropcap-scrutinizer-v26-i.png 331 KB
- examples/drop-caps/output/dropcap-scrutinizer-v26-i.svg 45 KB
- examples/drop-caps/output/marginalia-dropcap-textures.css 89 KB
- examples/drop-caps/output/preview-css-composite.html 2.0 KB
- examples/drop-caps/output/preview-marginalia-variants.html 2.3 KB
- examples/drop-caps/output/preview-scrutinizer-v26.html 48 KB
- examples/engine-sectors-overlay/L1-mark-256-dark.png 76 KB
- examples/engine-sectors-overlay/L1-mark-256-dark.svg 18 KB
- examples/engine-sectors-overlay/L1-mark-256-light.png 79 KB
- examples/engine-sectors-overlay/L1-mark-256-light.svg 18 KB
- examples/engine-sectors-overlay/L1-mark-favicon-dark.png 15 KB
- examples/engine-sectors-overlay/L1-mark-favicon-dark.svg 18 KB
- examples/engine-sectors-overlay/L1-mark-favicon-light.png 15 KB
- examples/engine-sectors-overlay/L1-mark-favicon-light.svg 17 KB
- examples/engine-sectors-overlay/L2-wordmark-dark.png 354 KB
- examples/engine-sectors-overlay/L2-wordmark-dark.svg 182 KB
- examples/engine-sectors-overlay/L2-wordmark-light.png 371 KB
- examples/engine-sectors-overlay/L2-wordmark-light.svg 178 KB
- examples/engine-sectors-overlay/L3-diagram-dark.png 903 KB
- examples/engine-sectors-overlay/L3-diagram-dark.svg 787 KB
- examples/engine-sectors-overlay/L3-diagram-light.png 952 KB
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.
- 2d ago First seen · 245 lines · 101 tokens per session scan A cb1ec900ed72
muriel is a skill published in the GitHub repository andyed/muriel (19 stars, last pushed 3d ago), licensed MIT. It adds 101 tokens to every session and 2,630 once invoked, about $0.0005 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 skills, from other repositories
anydesign
Analyze images, websites, and Figma files to extract their design and generate a design.md with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest…
claude-design-idea-to-ready
Take a UI from a one-line idea to on-brand, shippable design with Claude, in the correct order — brand foundation first, then components, screens, interactions, accessibility, and only then generation via /design. Use whenever someone wants to design, redesign, or generate a screen, page, component, or onboarding flow…
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
ss-score
Score a visual artifact's implementation quality 0-100 against its composed StyleSeed rule set — category breakdown, evidence, and prioritized fixes.
ss-update
Check and update an existing StyleSeed installation by exact rule/skill revision, preserve project-owned design decisions, then recompile and verify the effective bundle.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.