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/smorand/mcp-htmleditor/skillnpx skills add smorand/mcp-htmleditor --skill skillgit clone --depth 1 https://github.com/smorand/mcp-htmleditorWrote 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/smorand/mcp-htmleditor/skill)<a href="https://agentmods.dev/skills/smorand/mcp-htmleditor/skill"><img src="https://agentmods.dev/badge/skills/smorand/mcp-htmleditor/skill.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 | $0.00000 | $0.04265 |
| Opus 5 | $0.00000 | $0.02132 |
| Sonnet 5 | $0.00000 | $0.00853 |
| Haiku 4.5 | $0.00000 | $0.00426 |
Grade A, and why
skill 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 3d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-htmleditor — Skill
Description
mcp-htmleditor est un éditeur WYSIWYG HTML piloté par LLM. Il combine:
- Un serveur HTTP local (port 7842 par défaut, port libre auto-choisi dans 7840-7849 si occupé, voir « plusieurs présentations en parallèle » plus bas) servant GrapesJS dans le navigateur
- Un serveur MCP exposant 6 outils pour que l'agent LLM contrôle le fichier HTML
- Des templates de référence et bootstrap pour démarrer rapidement
- Un export vers PPTX (python-pptx) et DOCX (pandoc)
L'agent modifie le fichier HTML sur disque; le navigateur se synchronise automatiquement via polling.
Choisir et créer depuis un template
Le template se choisit à la création du fichier, via mcp-htmleditor new <key>.
Il n'y a pas d'option --template sur serve: on crée d'abord, on édite ensuite.
mcp-htmleditor templates # liste les templates
mcp-htmleditor new ei ma-pres.html --serve # Euro-Information (slides)
mcp-htmleditor new carbon ma-pres.html --serve # IBM Carbon (slides)
mcp-htmleditor new medical pres-med.html --serve # Presentation medicale (teal/orange)
mcp-htmleditor new doc mon-rapport.html # Document standard
mcp-htmleditor new doc-perso mon-doc.html --serve # Document charte Perso
mcp-htmleditor new doc-ei note-ei.html --serve # Document Euro-Information
mcp-htmleditor new mail mon-mail.html --serve # Mail HTML Carbon leger
mcp-htmleditor new website mon-site.html --serve # Site web Carbon (nav, tabs, cartes)
Où sont stockés les templates
templates/
├── bootstrap/ ← points de départ (copiés par `new`)
│ ├── slides-ei-empty.html ← key: ei (Euro-Information)
│ ├── slides-empty.html ← key: carbon (IBM Carbon)
│ ├── slides-medical-empty.html ← key: medical (présentation médicale, source du CSS de la charte)
│ ├── document-empty.html ← key: doc (document standard)
│ ├── document-perso-empty.html ← key: doc-perso (charte Perso, Arial)
│ ├── document-ei-empty.html ← key: doc-ei (Euro-Information, Segoe UI)
│ ├── mail-empty.html ← key: mail (mail HTML Carbon leger)
│ └── website-empty.html ← key: website (site web Carbon: nav, hero, tabs, cartes, footer)
└── reference/ ← exemples complets (à consulter/cloner)
├── slides/
│ ├── euro-information.html ← EI: titre + agenda + contenu, logos embarqués
│ ├── example-ei-complete.html ← EI: 9 slides, gantt, schéma, tableau, image annotée
│ ├── ibm-carbon.html ← IBM Carbon: 9 slides, tous les composants
│ ├── medical.html ← medical: catalogue, une slide par data-slide-type (16)
│ ├── example-medical-complete.html ← medical: exemple riche de bout en bout
│ ├── presentation-standard.html
│ └── roadmap-one-pager.html
├── documents/
│ ├── report-standard.html ← rapport standard générique
│ ├── perso.html ← charte Perso: titre/sous-titre + h1-h5 + tableau + liste
│ ├── euro-information.html ← document EI: en-tête bleu + logo, headings bleus
│ ├── example-perso-complete.html ← exemple riche Perso (3 pages, figure PNG, sup/sub)
│ ├── example-ei-complete.html ← exemple riche EI (3 pages, figure PNG, sup/sub)
│ └── mail-carbon-example.html ← exemple riche mail Carbon leger (tables imbriquées, CSS inline)
└── websites/
└── ibm-carbon.html ← catalogue complet: variantes de nav, tabs, cartes, footer
What ships with it
14 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.
- checks/arch-diagram-checklist.md 12 KB
- types/annotated-image.md 7.6 KB
- types/arch-diagram.md 23 KB
- types/document.md 14 KB
- types/gantt.md 11 KB
- types/mail.md 9.3 KB
- types/medical.md 29 KB
- types/slides.md 27 KB
- types/tables.md 4.2 KB
- types/website.md 4.9 KB
- workflow-arch-qa.md 3.6 KB
- workflow-create.md 15 KB
- workflow-export.md 13 KB
- workflow-templates.md 3.2 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.
- 3d ago First seen · 250 lines · 0 tokens per session scan A ef1da5b9b86d
skill is a skill published in the GitHub repository smorand/mcp-htmleditor (0 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,265 tokens. 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 skills, from other repositories
design-system
Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
pptx-posters
Create and audit editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Use when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
pdf-design
Designs PDF reports and proposals from HTML with previews and branding. Use to create, export, or securely upload a PDF.
document-design
Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.
section-508
Expert Section 508 compliance advisor for US federal ICT accessibility. Use this skill whenever a user asks about Section 508, WCAG 2.0/2.1 AA for federal systems, VPAT or Accessibility Conformance Reports (ACR), accessibility audits, remediation planning, PDF accessibility, web or software accessibility, mobile…