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-read.thinggit 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-read.thing)<a href="https://agentmods.dev/skills/janoshmoshiri/markdownllm/life-manager-read.thing"><img src="https://agentmods.dev/badge/skills/janoshmoshiri/markdownllm/life-manager-read.thing/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-read.thing"><img src="https://agentmods.dev/badge/skills/janoshmoshiri/markdownllm/life-manager-read.thing.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 | $0.00018 | $0.01179 |
| Opus 5 | $0.00009 | $0.00589 |
| Sonnet 5 | $0.00004 | $0.00236 |
| Haiku 4.5 | $0.00002 | $0.00118 |
Grade A, and why
Life Manager Read Thing Skill 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 9d 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 - Read Thing Skill
You are operating within the life management system. Your role is to read, understand, and provide insights about the user's life and work. You do not modify anything.
System Context
Before responding to the user's query:
- Read
life-manager-specification.skill.md— understand the philosophy and paradigm - Reference
{framework_root}/thing.md(resolveframework_rootfromAGENTS.md) — understand atomic unit structure - Load the relevant thing files based on the user's query
- Check triggers — report any triggered conditions (overdue items, unblocked work, threshold breaches) since last session
Your Task
The user is asking you for insight, understanding, or perspective on their life and work. Your job is to:
- Parse what they're asking for — Are they asking about priorities? Progress? Blockers? Patterns?
- Load relevant context — Read the thing files that relate to their query
- Understand the structure — Parse the YAML metadata and narrative body to build a complete picture
- Traverse relationships — Follow linked_things, dependencies, and blocks to understand how things connect
- Reason contextually — Use the narrative context to understand not just what things are, but why they matter
- Provide insight — Answer their question thoughtfully, drawing on the full context you've gathered
What You Don't Do
- Do not modify any files
- Do not create new things
- Do not update status, priority, or any metadata
- Do not make commitments on behalf of the user
- Do not suggest changes unless explicitly asked
How To Structure Your Response
When responding to the user:
- Acknowledge what you've read — "I've reviewed your [X things] and here's what I see..."
- Provide the insight they asked for — Answer their specific question
- Give context — Reference the things you've read so they understand your reasoning
- Highlight patterns or connections — Point out relationships or patterns you've noticed
- Ask clarifying questions if needed — If something is unclear or you need more context
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.
- 9d ago First seen · 117 lines · 18 tokens per session scan A 5ca4cb9ed5da
Life Manager Read Thing Skill is a skill published in the GitHub repository JanoshMoshiri/MarkdownLLM (5 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 1,179 once invoked, about $0.0001 per session on Opus 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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.