Obsidian Mind is an Obsidian vault that stores notes, links, indexes, and other accumulated context so AI coding agents can retain memory across sessions. It is designed for Claude Code and also supports Codex CLI and Gemini CLI through shared hooks, commands, and vault data. Its catalogue add-ons package the vault’s commands, agents, skills, hooks, instructions, settings, plugin, and MCP integration.
Borrowing it
Nothing to install: this file belongs to breferrari/obsidian-mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/breferrari/obsidian-mind/main/.claude/commands/om-intake.mdgit clone --depth 1 https://github.com/breferrari/obsidian-mindWrote 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/breferrari/obsidian-mind/om-intake)<a href="https://agentmods.dev/commands/breferrari/obsidian-mind/om-intake"><img src="https://agentmods.dev/badge/commands/breferrari/obsidian-mind/om-intake.svg" alt="Measured on agentmods" 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 | $0.01036 |
| Opus 5 | $0.00016 | $0.00518 |
| Sonnet 5 | $0.00006 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
om-intake 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 7d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Intake
Scans work/meetings/ for unprocessed meeting exports and routes everything to the correct vault locations automatically. No arguments needed — just drop files and run.
Usage
/om-intake
Drop any exported or raw meeting note into work/meetings/ first. Run this command after. Naming convention: YYYY-MM-DD <Topic or Person>.md.
Workflow
1. Scan the Inbox
List all .md files in work/meetings/ excluding README.md. If the folder is empty, say so and stop.
For each file found, read the full content before doing anything else.
2. Identify Meeting Type
For each note, determine what kind of meeting it was:
- 1:1 — between two people; personal, career, feedback, or relationship content
- Project meeting — status update, check-in, or planning session tied to a specific project
- Team meeting — standup, sprint planning, retrospective, or all-hands
- Decision meeting — primary purpose was to reach a decision
- Mixed — multiple types in one note (process each piece separately)
Use the note's content, title, and any attendee list to make this call.
3. Search for Related Vault Context
Before routing, run qmd query "<meeting topic or person name>" to find existing notes the content should attach to. Prefer appending to existing notes over creating new ones for small updates.
4. Route Content
Apply these routing rules to each piece of content:
| Content Type | Destination |
|---|---|
| 1:1 with a specific person | Create work/1-1/<Person> YYYY-MM-DD.md using 1:1 note structure |
| Project status update | Append to relevant work/active/<Project>.md |
| New project or initiative not in vault | Create work/active/<Project>.md |
| Decision reached | Create Decision Record in work/ + add to Decisions Log in work/Index.md |
| Action item / open task | Append as - [ ] to the relevant work note |
| Win or recognition | Add to perf/Brag Doc.md with link to source note |
| New person mentioned not in vault | Create stub in org/people/<Name>.md |
| Blocker identified | Append to relevant work/active/ note under ## Blockers or ## Open / Next Steps |
| Question raised but unanswered | Append to relevant note under ## Open Questions |
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.
- 7d ago First seen · 142 lines · 32 tokens per session scan A ba8c1d92cd29
om-intake is a command published in the GitHub repository breferrari/obsidian-mind (4,610 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,036 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
kb-ingest
Ingest external material into Sources/ inside the bound project KB, then update registry, index, and daily note as needed.
kb-promote
Promote durable content from Daily or source notes into canonical Knowledge, Experiments, Results, Results/Reports, or Writing notes.
obsidian-compatible-commands
Generated by python scripts/wiki.py obsidian export.
daily-okr
Run a daily knowledge compound loop (7 KR). Invoke with /daily-okr or "start my daily review".
session-learn
Extract knowledge from the current session. Invoke with /session-learn or "extract this session".
patterns
Scan recent sessions for recurring patterns and turn them into captures (rules, concept notes, writing seeds).