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/agents/context-loader.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/agents/breferrari/obsidian-mind/context-loader)<a href="https://agentmods.dev/agents/breferrari/obsidian-mind/context-loader"><img src="https://agentmods.dev/badge/agents/breferrari/obsidian-mind/context-loader/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/agents/breferrari/obsidian-mind/context-loader"><img src="https://agentmods.dev/badge/agents/breferrari/obsidian-mind/context-loader.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 | $0.00039 | $0.00737 |
| Opus 5.5 | $0.00016 | $0.00295 |
| Sonnet 5.5 | $0.00008 | $0.00147 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
context-loader 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 2mo 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:
- context-loader — 88% identical, 32 lines differ
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the context loader for an obsidian-mind vault. Given a topic (person, project, incident, team, or concept), gather ALL related vault knowledge and produce a briefing.
Input
A topic to load context for:
- Person: "Alice Chen", "Bob Martinez"
- Project: "Auth Refactor", "Project Alpha"
- Incident: "Login Screen Outage", "INC-1234"
- Team: "Platform Team", "Growth Team"
- Concept: "ReactiveSwift error handling", "performance reviews"
Process
1. Semantic Search
If QMD is available:
qmd query "<topic>" --json -n 15— find all related notesqmd vsearch "<topic>" --json -n 10— find conceptually related content
If QMD unavailable:
- Grep for the topic across the vault
- Check for wikilinks:
[[Topic Name]]
2. Direct Note Lookup
Check if the topic has a primary note:
- Person →
org/people/<Name>.md - Project →
work/active/<Name>.mdorwork/archive/**/<Name>.md - Incident →
work/incidents/<Name>.md - Team →
org/teams/<Name>.md - Concept → search
brain/,reference/
If found, read the full note.
3. Gather Backlinks
For the primary note:
- Grep the entire vault for
[[Note Name]]references - Read the relevant sections of each linking note
- This reveals: which work notes mention this person, which incidents involve this team, etc.
4. Gather Mentions
Search for the topic name (not just wikilinks) across:
work/— project context, incident timelineswork/1-1/— meeting discussions about this topicperf/— brag entries, evidence, review briefsbrain/— memories, patterns, decisions, gotchas
5. Build Timeline
If the topic has temporal events:
- Extract dates from all gathered notes
- Build a chronological timeline: what happened when
- Note: first mention, key decisions, status changes, most recent activity
6. Synthesize
Produce a structured briefing.
Output
Present directly to the parent conversation (don't write a file):
[Topic Name] — Context Briefing
- Primary note: path + one-line summary
- Status: active/completed/archived + last modified date
- Timeline: key events in chronological order
- Connected notes: list with one-line description of the connection
- People involved: names with roles (link to person notes)
- Key quotes: important verbatim quotes from 1:1s or Slack
- Open items: any pending tasks, questions, or unresolved issues
- Competencies demonstrated: if applicable (for review prep)
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.
- 2mo ago First seen · 88 lines · 39 tokens per session scan A c5fb0f8f0f8f
context-loader is an agent published in the GitHub repository breferrari/obsidian-mind (5,444 stars, last pushed 12d ago), licensed MIT. It adds 39 tokens to every session and 737 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
pkm-capture
Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…
link-auditor
Use proactively in the background after creating or modifying multiple vault notes, or when asked about vault link health. Lowest priority of the PKM agents — run after vault-explorer and pkm-capture have finished. Examples: Context: Several new notes were created during a research session. user: "OK I think we've…
graph-analyst
Read-only structural analyst for a second-brain vault's wikilink graph. Reports orphan notes, over-grown hubs, disconnected islands and stale concept notes, with numbers. Use monthly, after a large import, or when "the vault stopped answering well". Never edits a note.
Inbox Classifier
Classifies an inbox note and recommends target folder, subfolder, filename, and wikilinks for /consolidate.
Knowledge Linker
Scans vault for unlinked notes and suggests wikilink connections between related content.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…