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 JanoshMoshiri/MarkdownLLM --skill life-manager-specificationgit clone --depth 1 https://github.com/JanoshMoshiri/MarkdownLLMWrote 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/janoshmoshiri/markdownllm/life-manager-specification)<a href="https://agentmods.dev/skills/janoshmoshiri/markdownllm/life-manager-specification"><img src="https://agentmods.dev/badge/skills/janoshmoshiri/markdownllm/life-manager-specification/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/janoshmoshiri/markdownllm/life-manager-specification"><img src="https://agentmods.dev/badge/skills/janoshmoshiri/markdownllm/life-manager-specification.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 | $0.00019 | $0.01379 |
| Opus 5.5 | $0.00008 | $0.00552 |
| Sonnet 5.5 | $0.00004 | $0.00276 |
| Haiku 4.5 | $0.00002 | $0.00138 |
Grade A, and why
Life Manager Specification 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 2mo 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Life Manager Specification
Philosophy
This is not an app. It is a paradigm shift in how life management works.
Traditional apps separate concerns: input happens through UI, processing happens in code, output is notifications and data views. You think about wiring these together, building conditional logic, managing state in databases.
This system inverts that model entirely.
Processing: A capable LLM agent becomes your reasoning engine. The agent understands context, makes sense of complexity, handles ambiguity, reasons about priorities and dependencies. This is not rule-based logic—it's semantic understanding.
Interface: Your phone is pure interface and notification hub. You talk to your agent. You receive reminders and calendar updates. The phone is how you interact and how you get notified.
Storage: Git repository with markdown files is your persistent state. Not because it's clever, but because it's durable, versioned, readable by human and agent alike, and completely vendor-agnostic. Your life data lives in markdown. The LLM reads it, reasons about it, updates it.
The Paradigm Shift
You stop thinking about "how do I build this app" and start thinking about "how do I structure my data so the agent can understand and reason about it."
The complexity doesn't disappear—it just moves. Instead of writing conditional logic and integration code, you're defining how the agent should think about your life. Instead of predefined schemas, you let structure emerge based on what your life actually needs.
How It Works
- Your life exists as a collection of "things" in a git repository
- Each thing is a markdown file with YAML metadata and narrative body
- When you need help, you talk to the agent (via your phone, via any interface)
- The agent reads the relevant things, understands the structure and context
- The agent reasons about what you're asking, what matters, what's next
- The agent updates your thing files, creates reminders, updates your calendar
- Your phone notifies you of changes and reminders
- You talk to the agent again with new information or requests
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.
- 2mo ago First seen · 117 lines · 19 tokens per session scan A db6b8e6a0822
Life Manager Specification is a skill published in the GitHub repository JanoshMoshiri/MarkdownLLM (5 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 1,379 once invoked, about $0.0001 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 2026-09-04.
Life Manager Specification compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Life Manager SpecificationJanoshMoshiri/MarkdownLLM | Skill | 5 | 4d ago | MIT | A | 19 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |