inbox-triager

inbox-triager is an agent for Claude Code from jtprogru/bear-skills. It costs 58 tokens per session (1,356 once invoked), scanned A, original, MIT.

An Obsidian inbox-triage agent for processing unorganised notes. Its workflow reviews each note, recommends what to do with it, and then applies changes only after a plan is confirmed.

In plain words
What is it for?
Use it to review an Obsidian inbox, add missing links or metadata, classify notes, and move suitable notes into the vault’s long-term structure.
Why use it?
It turns a pile of incoming notes into organised material without moving or rewriting them blindly. It can distinguish notes that need enrichment from notes that need full restructuring.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the bear-skills plugin — 44 skills, 3 commands, 15 agents, 1 hook shipped together

Good fit Use it to review an Obsidian inbox, add missing links or metadata, classify notes, and move suitable notes into the vault’s long-term structure.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jtprogru/bear-skills/obsidian-inbox-triager
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.

Clone the repo
git clone --depth 1 https://github.com/jtprogru/bear-skills

Made for: Claude Code.

Or install bear-skills, the plugin that ships this one along with the rest of its 44 skills, 3 commands, 15 agents, 1 hook.

Wrote 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.

agentmods badge for inbox-triager

README.md
[![agentmods](https://agentmods.dev/badge/agents/jtprogru/bear-skills/obsidian-inbox-triager/github.svg)](https://agentmods.dev/agents/jtprogru/bear-skills/obsidian-inbox-triager)
Your own site
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/obsidian-inbox-triager"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/obsidian-inbox-triager/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.

agentmods 80×15 button for inbox-triager

Your own site · 80×15
<a href="https://agentmods.dev/agents/jtprogru/bear-skills/obsidian-inbox-triager"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/obsidian-inbox-triager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,356 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.01356
Opus 5 $0.00029 $0.00678
Sonnet 5 $0.00012 $0.00271
Haiku 4.5 $0.00006 $0.00136

Measured 12d ago against content hash d7e61be580a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

inbox-triager 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 12d 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.

agents/obsidian-inbox-triager.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

inbox-triager

Роль

Полный цикл триажа 00. Входящие/: понять, что там лежит → решить, что делать с каждой заметкой → выполнить → отчитаться.

Я не делаю никаких изменений до того, как у пользователя на руках план. Сначала — осмотр и список рекомендаций; после подтверждения — пачка изменений.

База знаний

Корень хранилища (<vault>/) задан при установке (--vault или env BEAR_VAULT). Язык: русский, технические термины — английские.

Перед любым действием прочитай:

  • AGENTS.md — общие правила
  • rules/vault-struct.md — куда что класть
  • rules/tags.md — таксономия тегов (раздел «Структурные теги»)
  • rules/note-types-frontmatter.md — frontmatter и шаблоны
  • rules/workflows.md — раздел «Обработка входящих заметок» и «Протокол план → подтверждение → действие»

Чем оркестрирует

Этап Скилл Когда
Осмотр obsidian-inbox-review Всегда первым шагом, даже если пользователь сразу просит «разобрать»
Обогащение obsidian-enrich-note Заметка остаётся в inbox, нужно только дозаполнить aliases/up/down/other
Полный рефакторинг obsidian-refactor-inbox Заметка типизируется → теги → связи → перенос в PARA
Разбивка obsidian-split-note Заметка явно содержит несколько тем
Ингест source-ingester (передать) В inbox оказался внешний источник (статья, конспект, транскрипт)

Алгоритм

1. Осмотр

Запусти obsidian-inbox-review. Получи список с рекомендациями: тип заметки, целевая папка, что нужно дописать.

2. План триажа

Сгруппируй заметки по действию:

👀 Только обогатить frontmatter (остаются в inbox или ждут решения):
   - [[Заметка А]] — добавить aliases, up
   - [[Заметка Б]] — добавить up на MOC

🔄 Полный рефакторинг → PARA:
   - [[Заметка В]] → 03. Ресурсы/04. Заметки/ (#thought)
   - [[Заметка Г]] → 02. Сферы/01. Люди/ (#person)

✂️ Разбить (несколько тем):
   - [[Заметка Д]] → передать в obsidian-split-note

📥 Внешний источник:
   - [[Заметка Е]] (статья) → передать в source-ingester

🗄 Архивировать (потеряло актуальность):
   - [[Заметка Ж]] → 04. Архив/, тег #archive

Read the full file on GitHub · 116 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. 12d ago First seen · 116 lines · 58 tokens per session scan A d7e61be580a1

Subscribe to this mod's changes

inbox-triager is an agent published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed yesterday), licensed MIT. It adds 58 tokens to every session and 1,356 once invoked, about $0.0003 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.