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/danielmiessler/lifeos/htmlnpx skills add danielmiessler/LifeOS --skill htmlgit clone --depth 1 https://github.com/danielmiessler/LifeOSWhat 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 | $0.00131 | $0.00936 |
| Opus 5 | $0.00066 | $0.00468 |
| Sonnet 5 | $0.00026 | $0.00187 |
| Haiku 4.5 | $0.00013 | $0.00094 |
Grade A, and why
HTML scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://localhost:31337/notify \ How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML
Turns whatever the session just produced into one self-contained, designed HTML file and publishes it as an Artifact. Deterministic split: the model's only job is distilling the session output into a typed content JSON and picking a design register; Tools/Render.ts owns every layout, typography, and color decision.
Voice Notification
When executing a workflow, do BOTH:
-
Send voice notification:
curl -s -X POST http://localhost:31337/notify \ -H "Content-Type: application/json" \ -d '{"message": "Running the Render workflow in the HTML skill to build a designed HTML artifact"}' \ > /dev/null 2>&1 & -
Output text notification:
Running **Render** in **HTML**...
Workflow Routing
| Workflow | Trigger | File |
|---|---|---|
| Render | /HTML, "HTML artifact", "render this as HTML" |
Workflows/Render.md |
Quick Reference
- Renderer:
bun ~/.claude/skills/HTML/Tools/Render.ts --json content.json --register dossier --out artifact.html --schemaprints the content JSON shape with an example;--registerslists registers.- Registers:
dossier(dark ink-green / orange, condensed display + typewriter — evidence files, red teams, investigations) andledger(dark navy / gold, old-style serif — reports, finance, plans, comparisons). Alternate between them so consecutive outputs don't converge; add new registers to Render.ts rather than hand-styling one-offs. - Output is Artifact-CSP safe: inline CSS, fonts embedded as data URIs from local font files, zero external requests.
Gotchas
- DOM-render screenshot pipelines drop CSS pseudo-element generated content (counters,
::beforelabels render in the browser but vanish from DOM-render captures, and they're invisible to text extraction). Render.ts therefore emits all numbering and labels as real DOM text. Never add CSS counters to a register. (Discovered 2026-07-11.) - Artifacts block all external requests — a Google Fonts
<link>fails silently and you get the fallback stack. Embed via data-URI@font-face(Render.ts does this when the register's font file exists locally) or design on system stacks. - The artifact viewer wraps your file in its own document skeleton — emit
<title>+<style>+ body content only; no<!doctype>/<html>/<head>/<body>tags. - A published artifact is private to its owner's claude.ai account — verifying it in a browser signed into a different account/org 404s. Verify the render by serving the HTML file locally and capturing that; verify publication via the Artifact tool's
listaction. - Numbered section markers must mean something. Render.ts numbers sections (document order — legitimate). Don't number list items unless the content is a true sequence; use
listblocks with bold lead-ins instead.
What ships with it
2 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.
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.
- yesterday First seen · 65 lines · 131 tokens per session scan A f723636309c6
HTML is a skill published in the GitHub repository danielmiessler/LifeOS (18,798 stars, last pushed 17d ago), licensed MIT. It adds 131 tokens to every session and 936 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
mobile-harness
Portable Android and iOS device-control harness for agents. Use when an agent needs to control or automate Android/iOS devices — tap, swipe, screenshot, app control — locally (ADB/Portal/Simulator) or on Mobilerun cloud devices.
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
aster-cli
Guidance for using the aster CLI to work in a codebase with an AI agent: chat and edit code, run AI code reviews, apply fixes, and manage sessions, memory, and skills. Use when running or designing aster commands, reviewing a diff or PR with aster, or when the user mentions aster review, aster chat, aster fix, or…
aster-config
Reference for aster.yaml, covering review models, analyzers, focus areas, include/exclude globs, minconfidence, and the permissions block that gates edits. Use when creating or editing aster.yaml, choosing hypothesis/verify models, enabling semgrep or ast-grep, or configuring edit permissions.
aster-chat-sessions
Drive aster chat programmatically and manage sessions and memory: one-shot --print/--json answers, --messages-json for caller-owned history, --continue and --session persistence, --allow-edits gating, and the sessions/memory commands. Use when scripting aster chat, integrating it into an editor or agent, or inspecting…
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.