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.
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.
npx agentmods add commands/breferrari/obsidian-mind/om-humanizegit 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-humanize)<a href="https://agentmods.dev/commands/breferrari/obsidian-mind/om-humanize"><img src="https://agentmods.dev/badge/commands/breferrari/obsidian-mind/om-humanize.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 | $0.00023 | $0.00849 |
| Opus 5 | $0.00012 | $0.00425 |
| Sonnet 5 | $0.00005 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
om-humanize 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 6d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- humanize — 95% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit a note to match your writing voice. This is voice calibration, not pattern removal — learn HOW you write, not just what to avoid.
Usage
/om-humanize <file path or note name>
Workflow
1. Load Voice Samples
Read 2-3 recent notes you actually wrote or heavily edited to calibrate voice:
brain/North Star.md— how you write about yourself- The most recent
work/1-1/*.mdnote — natural conversational voice - Any brain note with your authentic writing style
Extract voice fingerprint: sentence length, punctuation habits, how you open sections, how you qualify statements, ratio of direct-to-hedged language, use of dashes and fragments.
2. Read Target Note
Read the note specified in $ARGUMENTS (resolve as wikilink name or file path).
Detect context from frontmatter and folder:
work/1-1/→ conversational, direct, uses "I", okay to be informalperf/review content → corporate-confident but human, evidence-based, respect charcountwork/incidents/→ precise, factual, timeline-oriented, no fillerbrain/→ terse shorthand, fragments okay- Default → colleague-to-colleague, like explaining something in a 1:1
3. Edit In-Place
Rewrite the note's content to match your voice. Key principles:
Voice rules (from samples):
- Direct statements, not hedged ones ("This was stressful" not "This presented some challenges")
- Match your natural rhythm — fragments, dashes, whatever you actually use
- Observations should be sharp, not softened
- A concise 600-char section is better than a padded 950-char one
Anti-patterns (kill these):
- "Notably", "significantly", "demonstrates", "leveraged", "facilitated"
- "It's worth noting that..." — just note it
- "This showcases..." — just describe what happened
- Hedge stacking: "potentially", "arguably", "it could be said that"
- Empty transitions: "Moving forward", "In terms of", "With regard to"
- Passive voice where active is natural: "was identified" → "found"
- Bullet points that all start with the same word pattern
- Rhetorical questions followed by immediate answers
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.
- 6d ago First seen · 83 lines · 23 tokens per session scan A bc800052b91c
om-humanize is a command published in the GitHub repository breferrari/obsidian-mind (4,599 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 849 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.
Other commands, from other repositories
session-stop
Stop recording and save this agent session to the project ledger.
ox-prime
Load SageOx team context for this AI coworker session.
setup
Configure Vault PKM plugin — set vault path, API keys, and verify setup.
setup-mcp-claude-code
Build and register the Contorium MCP server for Claude Code or Cursor Agent.
refresh-context
Re-snapshot Core Context.md from (optional) mothership system files + key personal essays. Run when mothership files change, when new essays signal philosophy shift, or when snapshot is older than 30 days.
read-paper
Read a PDF and auto-generate a structured paper note. Output defaults to unreviewed and must pass /review-note before being citable by the wiki.