LifeOS is an AI-assisted personal operating system that records a person’s goals, values, context, and current situation to help move them toward a desired future state. It supports work such as building applications, starting businesses, and creative projects. Its catalogue entries extend the system through skills, hooks, agents, and commands.
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 danielmiessler/LifeOS --skill richformatgit clone --depth 1 https://github.com/danielmiessler/LifeOSWrote 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/danielmiessler/lifeos/richformat)<a href="https://agentmods.dev/skills/danielmiessler/lifeos/richformat"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/richformat/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/danielmiessler/lifeos/richformat"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/richformat.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 | $0.00164 | $0.03101 |
| Opus 5.5 | $0.00066 | $0.01240 |
| Sonnet 5.5 | $0.00033 | $0.00620 |
| Haiku 4.5 | $0.00016 | $0.00310 |
Grade A, and why
RichFormat 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 today.
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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RichFormat
Contents: Ideal State · Anti-criteria · Intent Routing · What it draws · The LifeOS rule · Tool contracts · Data & Config · Gotchas · Examples
A function-hooks plugin that makes assistant replies faster to read in the terminal. Claude Code loads it from this folder in every interactive session. It hooks two events and nothing else:
prompt.composeadds one section to the system prompt that teaches the drawable conventions, in interactive terminal sessions only (Anti-criteria).classic.MessageDisplayreceives each batch of finished lines while an answer streams and returns the text the terminal shows in their place, with ANSI colour. That text is the answer's first and only copy. A drawable fence is held until it closes, then drawn whole (hooks/stream.ts).
Ideal State
- Every construct in What it draws that parses is drawn, never left as plain markdown: a
flowfence as boxed nodes, adifffence as numbered red and green lines, a fully marked VERIFY run as green and red marks, and a label line in its colour (the engine and pure-logic suites hold each). - The stored message never changes. The model, the transcript file and ctrl+o all see plain markdown.
- On any doubt the lines show as written: a fence that does not parse, a fence still open at the message's last flush, a thrown error, or the option switched off.
- Every answer prints exactly once, at any length, under the full statusline.
Anti-criteria
- The mod never hooks any event besides
prompt.composeandclassic.MessageDisplay; noui.renderhook on AssistantMessage comes back, even one that passes the answer straight through. - A finished answer is never repainted; this mod shapes first draws only.
- The prompt section is never added outside an interactive terminal session, so iMessage bridges,
-pruns, teammates and SDK sessions never learn a convention they cannot draw. - A list is never split between two renderers: a 💡 line inside a list or table, a ✓ bullet outside VERIFY, a VERIFY run with any unmarked or nested bullet, and anything inside another code fence stay plain.
- A double-printed answer is never fixed by turning the statusline off.
What ships with it
19 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.
- hooks/banner.ts 11 KB runs code
- hooks/charts.ts 10 KB runs code
- hooks/chips.ts 659 B runs code
- hooks/core.ts 27 KB runs code
- hooks/diff.ts 3.8 KB runs code
- hooks/enrich.ts 6.4 KB runs code
- hooks/flow.ts 9.0 KB runs code
- hooks/glyph-core.ts 8.2 KB runs code
- hooks/hooks.json 34 B
- hooks/palette.ts 1.7 KB runs code
- hooks/register.tsx 3.7 KB
- hooks/stream.ts 18 KB runs code
- hooks/style.ts 1.1 KB runs code
- hooks/table.ts 17 KB runs code
- hooks/workflow.ts 8.3 KB runs code
- Setup.md 1.6 KB
- tests/engine.test.tsx 4.1 KB
- tests/hooked-events.check.ts 2.6 KB runs code
- tsconfig.json 396 B
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.
- today First seen · 124 lines · 164 tokens per session scan A 831dccdef029
RichFormat is a skill published in the GitHub repository danielmiessler/LifeOS (19,616 stars, last pushed today), licensed MIT. It adds 164 tokens to every session and 3,101 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-28.
Other skills, from other repositories
artifact-design
Designing and building any user-facing surface: a web page, landing page, dashboard, report, HTML document, email, or a component inside an existing app. Use when asked to build, style, redesign, or beautify UI, when writing HTML/CSS or a React/Vue/Svelte component that a person will look at, and when a generated page…
figma-to-coded-html
Convert Figma designs into self-contained, shareable single-file HTML with all UI elements coded in HTML/CSS/SVG and only actual photographs embedded as inline base64. Use this skill whenever the user asks to convert a Figma file/URL to HTML, export Figma designs as code, create HTML from Figma, turn a Figma mockup…
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
design-html
Design finalization: generates production-quality Pretext-native HTML/CSS. Works with approved mockups from /design-shotgun, CEO plans from /plan-ceo-review, design review context from /plan-design-review, or from scratch with a user description. Text actually reflows, heights are computed, layouts are dynamic. 30KB…
design-system
A visual guide for designing websites, landing pages, and interface components with consistent colors, fonts, layouts, buttons, cards, and forms. It includes guidance for tools such as shadcn/ui and Tailwind CSS.
visual-verdict
A strict comparison method for judging a generated user-interface screenshot against one or more reference images. It returns a score, a pass or revision decision, identified differences, and suggested changes.