Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jtprogru/bear-skillsnpx agentmods add skills/jtprogru/bear-skills/obsidian-ingestWrote 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/jtprogru/bear-skills/obsidian-ingest)<a href="https://agentmods.dev/skills/jtprogru/bear-skills/obsidian-ingest"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/obsidian-ingest/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/jtprogru/bear-skills/obsidian-ingest"><img src="https://agentmods.dev/badge/skills/jtprogru/bear-skills/obsidian-ingest.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 | $0.00087 | $0.03114 |
| Opus 5 | $0.00044 | $0.01557 |
| Sonnet 5 | $0.00017 | $0.00623 |
| Haiku 4.5 | $0.00009 | $0.00311 |
Grade A, and why
obsidian-ingest 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 10d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
obsidian-ingest — Ингест знаний в SecondBrain
Скилл-координатор пайплайна ингеста: взять один markdown-источник, понять, какие знания в нём скрыты, и создать нужные файлы. Форматирование, frontmatter и связи — часть ингеста, ты делаешь их сам.
Правила хранилища из .agents/rules/ (frontmatter, атомарность, стиль, теги, именование) загружены в каждую сессию — следуй им, здесь описан только пайплайн. Для внешнего research по необходимости подключай .agents/skills/deep-research/SKILL.md.
Шаг 1. Прочитай и пойми источник
Большой источник (файл или URL больше ~15 КБ) не читай в основной контекст. Запусти субагента obsidian-source-reader (Agent tool, subagent_type obsidian-source-reader), передав путь или URL, — он прочитает источник целиком и вернёт структурированную выжимку: метаданные, главный тезис, кандидатов в атомарки с цитатами-опорами, противоречия, термины. Формат выжимки зафиксирован в самом агенте (.agents/agents/obsidian-source-reader.md).
Дальше основная сессия работает только с выжимкой: ищет дубликаты в базе, составляет план, создаёт заметки, расставляет связи. Малый источник (меньше ~15 КБ) читай напрямую, как обычно.
По итогам чтения или выжимки определи: тип контента, главную тему (одна фраза), домен (теги таксономии) и стартовый confidence (medium если источник один).
Шаг 1.5. Внешний research (опционально)
Запускай только при срабатывании триггера: источник старше 2 лет на технологическую тему; тезисы с «многие/часто/обычно» без конкретики; инструмент или паттерн, которого нет ни в одной существующей заметке (проверь rg); единственный источник просится в confidence: high; пользователь явно попросил «обогати», «дополни», «исследуй».
Если триггеров нет — переходи к шагу 2. Методичка — deep-research. Потолок — 3–5 внешних источников: цель — обогатить этот источник, а не написать обзор по теме. Запросы формулируй на текущей дате и по-английски, результаты записывай по-русски.
По итогам зафиксируй для шагов 4–5: что подтверждается (повод для confidence: high), что расширяется (абзац в литературке и атомарках), что противоречит (callout + contradicts).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 221 lines · 87 tokens per session scan A c6039e3184c9
obsidian-ingest is a skill published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 23d ago), licensed MIT. It adds 87 tokens to every session and 3,114 once invoked, about $0.0004 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
session-handoff
Write a handoff file so a stuck session can resume in the other tool without losing context. Use when asked to "hand this off", "switch to Codex", "switch to Claude Code", "write a handoff", "I'm stuck, try the other tool", or when a session has burned several attempts on the same problem.
configuring-grove
Use when a user wants to set up or change Grove's configuration, for a host/user or for a project. Covers the global user config, the committed project config, machine-local overrides, agents, init scripts, containers, tmux and peek tuning, the TUI theme, the daemon auth, notifications, and ticket providers (Gitea…
add-teams
Adds Microsoft Teams connector to a Power Apps code app. Use when sending Teams messages, posting to channels, or integrating with Teams chat.
sys-configure
Configure Claude Octopus — redirects to /octo:setup interactive wizard.
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.