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 shortcutsgit 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/shortcuts)<a href="https://agentmods.dev/skills/danielmiessler/lifeos/shortcuts"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/shortcuts/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/shortcuts"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/shortcuts.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 | $0.00116 | $0.01166 |
| Opus 5.5 | $0.00046 | $0.00466 |
| Sonnet 5.5 | $0.00023 | $0.00233 |
| Haiku 4.5 | $0.00012 | $0.00117 |
Grade A, and why
Shortcuts 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 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.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shortcuts
Turn GUI-only macOS Shortcuts into callable LifeOS automation. Shortcuts reaches Apple-only surfaces (HomeKit/Home, native system actions, app intents) that have no other automation path. Computer use is slow and pixel-fragile, while the shortcuts CLI is fast and deterministic but can only run shortcuts, never build them. So each capability is built once (BuildShortcut) and is plain CLI from then on (RunShortcut, through Tools/Shortcuts.ts). This is CLI-first doctrine applied to the no-API problem.
Ideal State
- Each Apple-only capability is built once as a Shortcut under the exact name its consumers call, and is proven by a
runwhose output matches the spec, never by how the editor looks. - Every later use is plain CLI through
Tools/Shortcuts.tsorshortcuts run, with no pixels and no computer use. - A failed run or missing shortcut is diagnosed against the exact registered names, so a case or whitespace mismatch is caught before anything is rebuilt.
Intent Routing
| Intent | Trigger | File |
|---|---|---|
| BuildShortcut | "build a shortcut", "create a shortcut", "set up the X shortcut" | Intents/BuildShortcut.md |
| RunShortcut | "run the X shortcut", "invoke X", any consumer calling a built shortcut | Intents/RunShortcut.md |
| ListShortcuts | "list shortcuts", "what shortcuts exist", "does X exist" | Intents/ListShortcuts.md |
| File | Read when |
|---|---|
Setup.md |
first-time setup, a worked example of adding your own shortcut, and the read-only proof commands |
Gotchas
- Creation is GUI-only: there is no
shortcuts create. TheshortcutsCLI runs, lists, and views, but cannot author. Never claim a shortcut was "built" via CLI. - Name matching is exact, case and spaces included.
shortcuts run "Casa Set Zone 1 Temp"fails silently-ish (nonzero exit) if the registered name iscasa set zone 1 tempor has a trailing space. Confirm withexistsafter building, register the exact string a consumer expects, and on a nonzerorunwith no clear error, diff the target string againstlistbefore rebuilding anything. - Input arrives on stdin; output is whatever the last action returns. The CLI pipes
--inputto the shortcut's stdin and captures the final action's output on stdout; without a final output action, stdout comes back empty.
What ships with it
5 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 · 73 lines · 116 tokens per session scan A 49fada6b888d
Shortcuts is a skill published in the GitHub repository danielmiessler/LifeOS (19,631 stars, last pushed today), licensed MIT. It adds 116 tokens to every session and 1,166 once invoked, about $0.0005 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
intent-recognition
Load before you build any new kept workflow or Agent. It decides which one to build, or what to ask first. Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the…
workflow
A workflow skill for embedded-device projects that plans and runs building, flashing, debugging, observing, and diagnosis tasks.
todoocard
A skill family for sending content to TodooCard, a six-colour electronic-paper display. It includes shared device setup and Bluetooth transfer, plus a route for the included nearby-food suggestion feature.
bee-actions
Act back on the owner's Bee wearable — the TOOL half of the Bee integration (channels-vs-tools split). The Bee CHANNEL (ag2-sparrow's sources/bee.py watcher) pushes captured events AT the agent as ambient tasks; this skill is what the agent CALLS to read Bee's data surfaces and mutate them.
pwn-ffi-adalmpluto-ad9361
Drive PWN::FFI::AdalmPluto::Ad9361 from pwneval.
long-running-work
Carrying complex coding and project work through commands that take minutes or hours: evals, benchmarks, full builds and test suites, migrations, servers, multi-round runs. Use when a command may run past a few minutes, timed out once, or when the task spans several rounds of run, read results, fix, run again.