context-loader

A context-gathering tool for an Obsidian-Mind vault, a folder of connected Markdown notes. Given a person, project, incident, team, or concept, it collects related notes, links, mentions, and timeline details into a briefing.

In plain words
What is it for?
Use it to prepare for work involving a person, project, incident, team, or technical concept by finding the main note and the surrounding history.
Why use it?
It reduces the need to search through scattered notes manually and helps reveal related information that uses different wording. The result brings the relevant background into one summary.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/breferrari/obsidian-mind/context-loader
Clone the repo
git clone --depth 1 https://github.com/breferrari/obsidian-mind

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00737
Opus 5 $0.00019 $0.00368
Sonnet 5 $0.00008 $0.00147
Haiku 4.5 $0.00004 $0.00074

Measured 2d ago against content hash c5fb0f8f0f8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/context-loader.md · 88 lines

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 notes
  • qmd 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>.md or work/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 timelines
  • work/1-1/ — meeting discussions about this topic
  • perf/ — brag entries, evidence, review briefs
  • brain/ — 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)

Read the full file on GitHub · 88 lines

Changes

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.

  1. 2d ago First seen · 88 lines · 39 tokens per session scan A c5fb0f8f0f8f

Subscribe to this mod's changes

context-loader is an agent published in the GitHub repository breferrari/obsidian-mind (4,588 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 737 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.

Related

Other agents, from other repositories

wiki-ingest

Read-only ingestion worker for one already-captured source. Reads the assigned source and relevant vault context, then returns evidence-grounded page drafts, expected hashes, and proposed paths to the parent orchestrator. It never writes or applies the shared transaction.

AgriciDaniel/claude-obsidian · 53 tokens

supply-chain-analyst

Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…

sageox/ox · 166 tokens

Knowledge Linker

Scans vault for unlinked notes and suggests wikilink connections between related content.

onebrain-ai/onebrain · 20 tokens

canvas-composer

Content strategist for canvas text nodes. Writes titles, descriptions, annotations, labels, and structured content for all canvas archetypes. Follows the 15-30 visible nodes per viewport principle. Content is scannable: headers, bullets, bold. Max 200 words per text node. Context: /canvas generate needs slide content…

AgriciDaniel/claude-canvas · 125 tokens

index

Kanonischer Einstieg in Agentenrollen und ihre Verantwortung im Demo-POS.

vincentmumme/personalos-boilerplate · 0 tokens

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…

AdrianV101/obsidian-pkm-plugin · 476 tokens