obsidian-second-brain turns an Obsidian vault into persistent, searchable memory for Claude Code and other command-line coding agents, storing knowledge as linked Markdown notes. It is for developers, founders, writers, and researchers who want agents to retain project context across sessions. Its catalogue entries provide commands, hooks, a plugin, a skill, and instructions for capturing, finding, and maintaining that memory.
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.
git clone --depth 1 https://github.com/eugeniughelbur/obsidian-second-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/commands/eugeniughelbur/obsidian-second-brain/obsidian-calendar)<a href="https://agentmods.dev/commands/eugeniughelbur/obsidian-second-brain/obsidian-calendar"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-calendar/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/commands/eugeniughelbur/obsidian-second-brain/obsidian-calendar"><img src="https://agentmods.dev/badge/commands/eugeniughelbur/obsidian-second-brain/obsidian-calendar.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 | $0.00032 | $0.03724 |
| Opus 5 | $0.00016 | $0.01862 |
| Sonnet 5 | $0.00006 | $0.00745 |
| Haiku 4.5 | $0.00003 | $0.00372 |
Grade A, and why
obsidian-calendar 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the obsidian-second-brain skill. Execute /obsidian-calendar $ARGUMENTS:
One command for everything that touches the calendar, selected by the first word (the mode):
agenda [range]- read the calendar and write an AI-first snapshot to the vault (read-only on the calendar).reconcile [window]- flag commitments the vault implies that are NOT on the calendar (read-only; flags, never writes events).meeting [selector]- turn a calendar event into a meeting note in the vault.schedule <args>- create or move a calendar event (the only mode that writes to the calendar).
If no mode word is given, infer it: a bare range word (today, week, next-week, a date) means agenda; otherwise ask which mode. Default with no argument at all: agenda today.
All modes require a Google Calendar MCP. The claude.ai connector exposes mcp__claude_ai_Google_Calendar__list_calendars, list_events, get_event, create_event, update_event, suggest_time; if your calendar MCP namespaces its tools differently, use that server's equivalents. If no calendar MCP is connected, say so clearly and stop - do not fall back to asking the user to paste their calendar.
Always start by reading _CLAUDE.md (folder conventions, working hours) and CRITICAL_FACTS.md (timezone) if they exist. If neither declares a timezone, default to the session timezone and note that as a caveat. Resolve every folder per references/folder-map.md (wiki-style paths shown below).
Mode: agenda - read the calendar into a snapshot note
Range argument: today (default), tomorrow, week (current ISO week Mon-Sun), next-week, YYYY-MM-DD, or YYYY-MM-DD..YYYY-MM-DD.
- Resolve the range against the user's current date; convert start/end to ISO 8601 (
YYYY-MM-DDTHH:MM:SS+/-HH:MM) in the user's timezone, end bound exclusive at end-of-day local. list_calendarsonce, pick the primary (primary: true). Accept--calendars <id1>,<id2>to include more; otherwise primary only.list_eventswithtimeMin,timeMax,singleEvents: true,orderBy: "startTime"; filter cancelled events client-side.- For each event capture verbatim: id, htmlLink, summary, start, end, location, description, hangoutLink/conferenceData URL, attendees (email + displayName + responseStatus), organizer, status, recurringEventId.
- Cross-link attendees against the entities folder (resolved per
references/folder-map.md): match by full name then email local-part, fuzzy (handle missing diacritics/short forms). Found ->[[Person Name]]; not found -> plain name +(unknown person). - Detect quality issues: conflicts (overlapping intervals on one calendar), back-to-back stretches (3+ with no gap), focus gaps (working-hours blocks 09:00-18:00 local unless overridden, with no meeting), externally-organized events (organizer domain != user's).
- Write the snapshot (
type: agenda-snapshot, schema inreferences/ai-first-rules.md) to the agenda folder (resolved perreferences/folder-map.md- wiki-stylewiki/agenda/, Obsidian-styleAgenda/): single dayYYYY-MM-DD - <today|tomorrow|day>.md, weekYYYY-MM-DD - week.md(Monday prefix), rangeYYYY-MM-DD - range.md(start prefix). If one exists for the range, overwrite it (the calendar is the source of truth) and addsuperseded-at: <previous fetched-at>. The## For future agentpreamble must state the calendar is the source of truth, not this note, andfetched-atis the recency anchor. Body:## Range,## Summary,## Events(one### YYYY-MM-DD - <Weekday>subsection per day; each event a bullet with start-end, title,[[attendees]], location, conference link verbatim, andevent-id: <id>so other modes can locate it), then## Conflicts/## Focus blocks/## External organizersonly if present. - Append to the operation log (
Logs/YYYY-MM-DD.mdif the vault uses aLogs/folder - create today's file if needed - elselog.md):## [<iso>] agenda | <range-label> - <event-count> events, <conflict-count> conflicts. Inject (do not overwrite) a## Calendarlink into today's daily note. - Report: snapshot path, events per day, conflicts/back-to-back/focus blocks, external organizers, and any
(unknown person)attendees. Do not paraphrase event titles or infer attendees. If the range is empty, still write the snapshot (event-count: 0).
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.
- 12d ago First seen · 95 lines · 32 tokens per session scan A 35369fcf21e6
obsidian-calendar is a command published in the GitHub repository eugeniughelbur/obsidian-second-brain (4,415 stars, last pushed 5d ago), licensed MIT. It adds 32 tokens to every session and 3,724 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 2026-08-30.
Other commands, from other repositories
cierre
A sales call just ended: turn its transcript into the full follow-up (CRM, tasks, email draft, reminder, coaching).
deconstruct
First-principles analyst: surface hidden assumptions, find foundational truths, rebuild from scratch.
instinct-import
Import a portable YAML instinct pack with confidence-gated merge (Instinct Engine).
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).
second-brain-mapping
Map your vault: extract structured metadata from every typed file, surface cross-doc insights, optionally build a knowledge graph.
setup-vault-types
Configure which document types your vault uses (journals, books, meetings, clients, etc.) and scaffold extractors.