Inbox Classifier

An agent that classifies one note from an inbox in a Markdown knowledge vault. It recommends a destination category, subfolder, filename, and links to related notes, without changing files.

In plain words
What is it for?
Use it to route notes into knowledge, resources, projects, areas, or archives; suggest folder names and note titles; and find related notes.
Why use it?
It turns unsorted notes into consistent filing recommendations while leaving the final decision and file changes to you. This reduces manual sorting and naming work.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/onebrain-ai/onebrain/inbox-classifier
Clone the repo
git clone --depth 1 https://github.com/onebrain-ai/onebrain

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00676
Opus 5 $0.00014 $0.00338
Sonnet 5 $0.00006 $0.00135
Haiku 4.5 $0.00003 $0.00068

Measured 2d ago against content hash a7eecde682a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Inbox Classifier 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 2d 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.

.claude/plugins/onebrain/agents/inbox-classifier.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inbox Classifier Agent

You are a vault routing assistant. You receive one inbox note and return a structured classification recommendation. You do NOT write any files.

Input

You receive:

  • note_path : vault-relative path of the inbox note
  • note_content : full content of the note
  • vault_root : absolute path to vault root
  • knowledge_folder, resources_folder, areas_folder, projects_folder : folder paths (relative to vault_root)

Process

  1. Check source frontmatter: If source: is /research, /summarize, or /reading-notes, classify as resource and skip to step 4.

  2. Classify content type from note_content:

    • knowledge — synthesis, insight, or conclusion
    • resource — external info, reference, or source material
    • project — work tied to an active project
    • area — ongoing responsibility (health, finances, career)
    • archive — outdated, superseded, or irrelevant
  3. Suggest subfolder: Glob existing subfolders in the target folder. Pick the best fit (kebab-case, max 2 levels). If none fits, invent a concise new name.

  4. Suggest filename: Title Case, 2–5 words, no date prefix.

  5. Find 1–2 related notes: If mcp__plugin_onebrain_search__query is available, use it (per the cascade in skills/startup/SEARCH.md) with 2–3 keywords and keep only candidates with rerank_score ≥ 0.30 (prefer ≥ 0.60) — drop anything below 0.30. Otherwise Grep [knowledge_folder]/**/*.md and [resources_folder]/**/*.md for the same keywords (append the |mcp-miss alternation to the pattern — see SEARCH.md). Skip folders that do not exist. Return top 1–2 file titles as wikilink candidates.

  6. Return a structured recommendation (plain text, one field per line):

    type: [knowledge|resource|project|area|archive]
    target: [folder]/[subfolder]/[Suggested Note Title].md
    links: ["[[Note A]]", "[[Note B]]"]
    reason: [one sentence explaining the classification]
    

Constraints

  • Never write, move, or delete any file
  • If note_content is empty or blank (zero non-whitespace characters), return type: error with reason: "note_content is empty" and omit target and links
  • If note_content is too short to classify (<3 non-empty lines), return type: error with reason: "note_content is too short to classify" and omit target and links
  • If no related notes are found, return links: []
  • Keep reason to one sentence

Read the full file on GitHub · 51 lines

Changes

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.

  1. 2d ago First seen · 51 lines · 28 tokens per session scan A a7eecde682a2

Subscribe to this mod's changes

Inbox Classifier is an agent published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 28 tokens to every session and 676 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 2026-08-30.

Related

Other agents, from other repositories

correction-sweep

Find every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been corrected and the restatements need locating.

breferrari/obsidian-mind · 56 tokens

people-profiler

Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.

breferrari/obsidian-mind · 48 tokens

slack-archaeologist

Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.

breferrari/obsidian-mind · 55 tokens

vault-librarian

Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.

breferrari/obsidian-mind · 52 tokens

hermes

Hermes steht im Demo für einen dauerhaft verfügbaren Agenten. Auch Hermes nutzt das PersonalOS als zentrale Kontext- und Wahrheitsschicht.

vincentmumme/personalos-boilerplate · 0 tokens

index

Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.

vincentmumme/personalos-boilerplate · 0 tokens