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 isorensen/lox-brain --skill paragit clone --depth 1 https://github.com/isorensen/lox-brainWrote 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/isorensen/lox-brain/para)<a href="https://agentmods.dev/skills/isorensen/lox-brain/para"><img src="https://agentmods.dev/badge/skills/isorensen/lox-brain/para/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/isorensen/lox-brain/para"><img src="https://agentmods.dev/badge/skills/isorensen/lox-brain/para.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 | $0.00030 | $0.02942 |
| Opus 5 | $0.00015 | $0.01471 |
| Sonnet 5 | $0.00006 | $0.00588 |
| Haiku 4.5 | $0.00003 | $0.00294 |
Grade A, and why
para 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 8d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PARA — Content Organization for Obsidian
Configuration
This skill reads your Lox configuration from ~/.lox/config.json:
vault.preset: must bepara(this skill is designed for the PARA template)vault.local_path: path to your Obsidian vault (default:~/Obsidian/Lox)
If vault.preset is zettelkasten, this skill will warn and suggest using /zettelkasten instead.
Folder mapping:
| Bucket | Folder | Description |
|---|---|---|
| Projects | 2 - Projects/ |
Active efforts with a deadline or deliverable |
| Areas | 3 - Areas/ |
Ongoing responsibilities (no deadline) |
| Resources | 4 - Resources/ |
Reference material for future use |
| Archives | 5 - Archive/ |
Completed projects, inactive areas |
Content language defaults to pt-BR. Technical terms and code identifiers stay in English. If the project's primary language is different (detected from README, CLAUDE.md, or user preference), adapt accordingly.
Purpose
The PARA method (by Tiago Forte) organizes information by actionability, not by topic. This skill automates PARA classification, note creation, lifecycle transitions, and dashboard generation inside the user's Obsidian vault via the Lox MCP Server.
Why PARA for a second brain:
- Actionability-first sorting ensures active work stays visible and reference material stays accessible
- Lifecycle transitions (Project -> Archive, Resource -> Project) keep the vault current
- Dashboards per bucket provide instant situational awareness
- Cross-linking between buckets reveals how resources feed projects and areas
Modes of Operation
Mode 1: Ingest (default)
Trigger: /para or /para <content/url/idea>
Given content (text, URL, idea, or pasted material), classify it into the correct PARA bucket and create a note.
Workflow:
- Receive content — The user provides text, a URL, a concept, or raw material to capture.
- Classify — Determine the correct PARA bucket using these rules:
- Project: Has a deadline, deliverable, or end state. Ask: "Can this be completed?"
- Area: Ongoing responsibility with a standard to maintain. Ask: "Is this something I maintain indefinitely?"
- Resource: Reference material, topic of interest, useful information. Ask: "Might I need this later?"
- Archive: Completed or inactive. Ask: "Is this done or no longer relevant?"
- If ambiguous, ask the user. Never guess between Project and Area.
- Check for duplicates — Use
mcp__lox-brain__search_textto find existing notes on the same topic. If found, offer to update instead of creating a new note. - Create note — Write the note to the correct folder using
mcp__lox-brain__write_note. - Cross-link — Search for related notes in other buckets and add
[[wikilinks]]in the Related section. - Report — Show the created file path, bucket classification, and any cross-links added.
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.
- 8d ago First seen · 276 lines · 30 tokens per session scan A 383ccd36a3bf
para is a skill published in the GitHub repository isorensen/lox-brain (2 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 2,942 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
wiki-dashboard
Create dynamic, queryable dashboard views of the Obsidian vault using Obsidian Bases or Dataview. Use this skill when the user says "create a dashboard", "vault dashboard", "show all X as a table", "dynamic view", "query my vault", "build a content index", "show me all concepts/entities/projects", or wants a…
daily-update
Run the daily wiki maintenance cycle: check all source freshness, update the index, and regenerate hot.md. Use this skill when the user says "/daily-update", "run the daily update", "update everything", "morning sync", "refresh the wiki index", or when triggered by the launchd cron at 9 AM. Also use to set up or…
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
knowledge-base-management
A lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers.
graphify
Use when the user invokes /graphify or asks to build, update, or query a knowledge graph from a folder of files (code, docs, papers, notes, images). Triggers: 'map this codebase', 'graph my notes', 'what is connected across these files', 'community detection', 'GraphRAG', incremental graph update, Neo4j/SVG/GraphML…