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 skills add chadixearth/graphyloop --skill lifewood-brandinggit clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/skills/chadixearth/graphyloop/lifewood-branding)<a href="https://agentmods.dev/skills/chadixearth/graphyloop/lifewood-branding"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/lifewood-branding/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/skills/chadixearth/graphyloop/lifewood-branding"><img src="https://agentmods.dev/badge/skills/chadixearth/graphyloop/lifewood-branding.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 | $0.00167 | $0.05159 |
| Opus 5 | $0.00084 | $0.02580 |
| Sonnet 5 | $0.00033 | $0.01032 |
| Haiku 4.5 | $0.00017 | $0.00516 |
Grade A, and why
lifewood-branding 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 6d 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 — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lifewood Branding
This skill governs how Lifewood deliverables look and compose. Document-building mechanics (python-pptx, fpdf2, docx) live in the pptx, pdf, or docx skills. This skill owns brand compliance and layout discipline.
1. Brand assets
Logo files in assets/. Never recolor, redraw, crop, distort, rotate, or re-typeset. Place the file as-is.
| File | Use on |
|---|---|
assets/lwlogo_lightmode.png |
Light backgrounds (Paper, White, Sea Salt) |
assets/lwlogo_darkmode.png |
Dark backgrounds (Dark Serpent, Castleton Green) |
assets/LW_Color.jpg |
Internal reference only — never in output |
Logo native ratio: ~5.5:1 (1655×300). Preserve exactly when sizing. Both have transparent backgrounds.
2. Color palette
| Name | Hex | Role |
|---|---|---|
| Paper | #F5EEDB |
Soft background / dark-bg text |
| White | #FFFFFF |
Background |
| Sea Salt | #F9F7F7 |
Background (preferred default) |
| Castleton Green | #046241 |
Headings |
| Dark Serpent | #133020 |
Subheadings + body text |
| Saffron | #FFB347 |
Accent — rules, callout fills, chart highlights, hexagon |
| Earth Yellow | #FFC370 |
Accent — softer highlight, fills |
Derived tints (surfaces only, never text):
#EFEAD9— inline-code chips, table header fills#E8E5DF— hairline rules and dividers (0.5–1pt)
Assignment rules (one place, no repetition):
- Backgrounds:
#F9F7F7(preferred) or#FFFFFF. - Headings (H1/H2):
#046241. - Subheadings + body:
#133020. - Accents:
#FFB347/#FFC370only. Never for body text. - Dark green backgrounds: text flips to
#F5EEDB/#FFFFFF; use dark-mode logo.
3. Typography
- Font: Manrope. Fallback chain: Inter → Helvetica Neue → Arial → sans-serif.
- Monospace: JetBrains Mono → SF Mono → Consolas → Menlo → Courier New.
- H1 (doc title): weight 800, 26–32pt,
#046241. - H2 (
X.0section): weight 700, 17–20pt,#046241. Small Saffron section number above it. - H3 (
X.1sub-section): weight 600, 12–13pt,#133020. - Body: 10.5–12pt, weight 400,
#133020, line height 1.4–1.5×. - Caption / table body: 9–10pt.
What ships with it
35 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.
- assets/LW_Color.jpg 43 KB
- assets/lwlogo_darkmode.png 20 KB
- assets/lwlogo_lightmode.png 20 KB
- assets/Manrope-Bold.ttf 93 KB
- assets/Manrope-ExtraBold.ttf 93 KB
- assets/Manrope-Regular.ttf 93 KB
- assets/Manrope-SemiBold.ttf 93 KB
- assets/manrope.zip 193 KB
- build_admin_manual.py 12 KB runs code
- build_developer_manual.py 31 KB runs code
- build_lifedata_user_manual.py 9.1 KB runs code
- build_lifedata_workflows.py 9.0 KB runs code
- build_overview_deck.py 4.9 KB runs code
- build_prmce_overview_deck.py 6.4 KB runs code
- build_prmce_user_manual.py 11 KB runs code
- build_prmce_workflows.py 13 KB runs code
- build_storyboard_studio_user_manual.py 17 KB runs code
- build_storyboard_studio_workflows.py 17 KB runs code
- build_user_manual.py 12 KB runs code
- build_workflows.py 11 KB runs code
- lifewood_deck_builder.py 88 KB runs code
- lifewood_design_variants.py 6.0 KB runs code
- lifewood_overview_generator.py 31 KB runs code
- lifewood_pdf_builder.py 74 KB runs code
- lifewood_pdf_design_system.py 20 KB runs code
- output/Developer_Manual.pdf 60 KB
- output/LifeData_Admin_Manual.pdf 52 KB
- output/LifeData_User_Manual.pdf 53 KB
- output/LifeData_Workflows.pdf 52 KB
- output/pdf_spec_lock.md 2.9 KB
- PPT_Master_Overview.pptx 69 KB
- REFERENCE.md 11 KB
- research_to_deck.py 4.3 KB runs code
- test_overlap.py 67 KB runs code
- User_Manual_Admin.pdf 60 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.
- 6d ago First seen · 312 lines · 167 tokens per session scan A 0c6eccd2da2f
lifewood-branding is a skill published in the GitHub repository chadixearth/graphyloop (2 stars, last pushed 24d ago), licensed MIT. It adds 167 tokens to every session and 5,159 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
kirby-panel-and-blueprints
Designs Kirby blueprints and Panel UI, including blueprint reuse/extends, programmable blueprints, and custom Panel fields/sections/areas. Use when changing the Panel experience or schema.
hipson-visual-experience-director
Use for visual direction, premium UI/UX art direction, motion interaction design, Codex-ready implementation briefs, and visual QA for web experiences.
hipson-premium-ui-ux
Use for premium UI/UX review and implementation planning in Hipson frontend projects, especially screenshot-backed landing pages, forms, visual polish, accessibility, responsive behavior, and design-agent packets.
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…
hipson-creative-frontend-motion-architect
Use for premium creative frontend, motion UI, scroll-driven animation, scrollytelling, cinematic landing pages, microinteractions, and implementation-ready prompts for React/Next.js frontend agents.
canvas
Instructions for rendering rich A2UI canvas elements to the chat interface.