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 presentationgit 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/presentation)<a href="https://agentmods.dev/skills/danielmiessler/lifeos/presentation"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/presentation/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/presentation"><img src="https://agentmods.dev/badge/skills/danielmiessler/lifeos/presentation.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 | $0.00223 | $0.03497 |
| Opus 5.5 | $0.00089 | $0.01399 |
| Sonnet 5.5 | $0.00045 | $0.00699 |
| Haiku 4.5 | $0.00022 | $0.00350 |
Grade A, and why
Presentation 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Presentation
Contents: Ideal State · Intent Routing · Data & Config · Gotchas · Examples
Talks, the slides behind them, and sales pitches, in three modes.
-
Lecture mode is a talk the speaker reads aloud from start to finish. The text is the content and the slides are there for pacing: a new slide every 15 to 30 seconds keeps the room watching, and each visual either supports the sentence being read or stays quiet. The source is a talk file (READ.md or SCRIPT.md); the deck is Keynote or HTML and is regenerated from it.
-
Deck mode is a deck where the slides carry the argument and the speaker glances at short cues. One claim per slide, the archetype chosen from the content, built as an HTML deck on the install's template and served with speaker view.
-
Pitch mode turns product documentation into a sales pitch: a first-person value story a buyer can retell, talking points, an elevator pitch, and for a full package a charcoal sketch (
Intents/Pitch.md, which absorbed the retired Sales skill).
Pick lecture mode when the speaker says they will read it, or hands over a talk file or dictation to turn into a talk. Pick deck mode for "make me a deck on X". Pick pitch mode for a sales pitch, narrative or package. When it is unclear, ask once.
Ideal State
- Every talk has an ISA before its slides do (principal, 2026-10-21). Its L3 names what the audience believes or does by the end, its criteria hold the time budget (spoken words at about 135 per minute, slide count) and the arc, and every cut, move or added slide traces to L3. A change of thesis updates the ISA first, then the order and the script.
- The speaker gets a deck they can present from: in lecture mode the notes are the talk file word for word, in deck mode every slide carries one claim and glanceable notes, and the talk file or script stays the one source the deck is rebuilt from.
- Everything real the talk names is on screen as itself: the speaker's registered things (
RealThings.json) with their registered picture, everything else sourced throughIntents/MediaSourcing.md. Every outside picture and clip has rounded corners (12 pt in Keynote, 12 px in an HTML deck) and its credit (film and year, site, publisher) in the small bottom-left source line, never the subtitle. - Generated art appears only where it carries something words cannot, and every number on a chart was verified this session or its source line says "illustrative". In lecture mode, on-slide text is a few words that echo the line being read, and where a visual adds nothing a plain text slide is right.
- Every slide passes the layout and playback checks in code (balanced, pictures filling the space they were given and never crowding the title, nothing overlapping, no large empty band, nothing waiting for a click) and was looked at as rendered pixels.
- A pitch tells one value story a buyer can retell, every product claim traced to a line in the source docs, with no feature-list sentence, and its sketch carries the same register and idea (
Intents/Pitch.md). - No deck reaches the speaker as a first draft: its slides passed a
slidescritique (References/QualityLoop.md) and it arrives throughDeliver.tsor as a served URL with the human-only keys stated.
What ships with it
30 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.
- DesignSystem.md 6.9 KB
- Intents/Build.md 2.0 KB
- Intents/CreateDeck.md 6.2 KB
- Intents/ExportToClaudeDesign.md 3.2 KB
- Intents/Keynote.md 7.1 KB
- Intents/KeynoteArt.md 5.8 KB
- Intents/KeynoteUpdate.md 4.8 KB
- Intents/MediaSourcing.md 6.6 KB
- Intents/Pitch.md 7.5 KB
- Intents/Present.md 2.6 KB
- Intents/Write.md 5.0 KB
- References/HtmlDecks.md 2.2 KB
- References/KeynoteGotchas.md 6.7 KB
- References/QualityLoop.md 1.4 KB
- References/TalkFiles.md 1.8 KB
- References/Tools.md 871 B
- ScriptFormat.md 2.3 KB
- Setup.md 6.9 KB
- Tools/Build.ts 15 KB runs code
- Tools/DeckCheck.ts 15 KB runs code
- Tools/Keynote.help.md 5.9 KB
- Tools/Keynote.ts 73 KB runs code
- Tools/KeynoteArt.help.md 2.8 KB
- Tools/KeynoteArt.ts 31 KB runs code
- Tools/KeynoteAutoplay.ts 16 KB runs code
- Tools/KeynoteMedia.ts 15 KB runs code
- Tools/KeynotePlayback.ts 7.7 KB runs code
- Tools/Layout.ts 36 KB runs code
- Tools/Present.ts 4.0 KB runs code
- Tools/RealThings.ts 7.0 KB runs code
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 · 122 lines · 223 tokens per session scan A 09bcfa460645
Presentation is a skill published in the GitHub repository danielmiessler/LifeOS (19,616 stars, last pushed today), licensed MIT. It adds 223 tokens to every session and 3,497 once invoked, about $0.0009 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
aster-planning
Create and execute structured plans for multi-step tasks. Use when the user gives a complex task spanning multiple files, asks for a plan or roadmap, says "break this down", or when a task cannot be completed in a single turn. Also use when the task touches several subsystems or the user wants to review the approach…
cli-toolbox
Getting exactly the output you need from CLI tools in one call: JSON flags, slicing, counting, non-interactive flags. Use when inspecting command output, working with JSON, probing HTTP, or when a command might prompt, page, or spew.
structural-edits
Structural search and rewrite with the astgrep and astedit tools. Use when the same pattern appears in many places, when text search matches comments or strings, or when a rename or codemod spans multiple files.
gpt-astra
Optimize agent instructions for GPT-6 Astra (Codex). Use when the user mentions Astra, Codex, GPT-6, or asks to audit/rewrite AGENTS.md, skills, or prompts for newer models.
i-have-adhd
Action-first, zero-filler replies for a reader who loses the thread in prose. Use when the user asks for terse or direct answers, says too long, get to the point, tldr, stop rambling, or when replies keep getting cut off or ignored.
echo-plugins
Build, validate, package, and stage optional Echo plugins using the Echo Plugin API v1 security and lifecycle contracts.