Loading plugin...

bedrock · Flowy

README

Bedrock is a Claude Code plugin that automates Obsidian vault management through AI-powered skills. It organizes knowledge into 7 entity types following adapted Zettelkasten principles — entity detection, bidirectional linking, ingestion from external sources, deduplication, and sync.

No build system. No runtime. Just markdown files, AI agents, and your Obsidian vault.

Features

8 AI-powered skills — setup, ask, teach, preserve, compress, sync, healthcheck, and vaults
7 entity types — actors, people, teams, topics, discussions, projects, and fleeting notes
External source ingestion — Confluence, Google Docs, GitHub repositories, and any file format supported by docling (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and more)
Bidirectional wikilinks — automatic cross-referencing with Obsidian graph view
Hierarchical tags — multi-dimensional filtering (type/, status/, domain/, scope/)
Zettelkasten structure — permanent, bridge, index, and fleeting note roles
Trunk-based git workflow — structured commit conventions built in

Installation

/plugin marketplace add iurykrieger/claude-bedrock
/plugin install bedrock@claude-bedrock

For local development:

claude --plugin-dir ./claude-bedrock

Quick Start

After installing, run the setup wizard:

/bedrock:setup

This will guide you through:

Language selection — choose the vault content language (default: English)
Dependency check — verify graphify is installed (required)
Vault objective — pick a preset (engineering team, product management, company wiki, personal second brain, open source project, or custom)
Scaffold — create directories, templates, config, and connected example entities

The setup creates all entity directories, copies templates, generates a vault-level CLAUDE.md, and scaffolds example entities with bidirectional wikilinks so you can see the graph in Obsidian immediately.

Skills

Skill	Purpose
`/bedrock:setup`	Interactive vault initialization and configuration
`/bedrock:ask`	Orchestrated vault reader — decomposes questions, searches graph and vault, cross-references entities
`/bedrock:learn`	Ingest external sources — extract and create entities
`/bedrock:preserve`	Single write point — detect, match, create/update entities with bidirectional links
`/bedrock:compress`	Deduplication and vault health — broken links, orphans, stale content
`/bedrock:sync`	Re-sync entities with external sources
`/bedrock:healthcheck`	Read-only vault health diagnostic — graphify-out integrity, orphans, dangling content, stale entries
`/bedrock:vaults`	Manage registered vaults — list, set default, remove

Vault Structure

your-vault/
├── actors/          # Systems, services, APIs (permanent notes)
├── people/          # Contributors, team members (permanent notes)
├── teams/           # Squads, organizational units (permanent notes)
├── topics/          # Cross-cutting subjects with lifecycle (bridge notes)
├── discussions/     # Meeting notes, conversations (bridge notes)
├── projects/        # Initiatives with scope and deadline (index notes)
└── fleeting/        # Raw ideas, unstructured captures (fleeting notes)

Each directory contains a _template.md defining the frontmatter schema for that entity type.

How It Works

Bedrock turns your vault into a living knowledge graph by combining 8 skills you invoke from Claude Code. You never write entities by hand — skills detect, create, and link them for you, with Obsidian rendering the result as a graph.

First-time use

Open a folder you want to turn into a vault (or an existing Obsidian vault).
Run /bedrock:setup — answers a few questions and scaffolds directories, templates, and example entities.
Open the folder in Obsidian. You'll already see a connected graph.

Day-to-day loops

Capture knowledge from a source — paste a Confluence page, Google Doc, GitHub repo, remote URL, or any local file (DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and any other docling-supported format) into /bedrock:learn. Bedrock extracts entities and writes them to the vault with bidirectional links.
Ask the vault questions — use /bedrock:ask for anything like "who owns the billing API?" or "what's the status of project X?". It searches the graph, follows wikilinks, and answers with citations.
Keep sources fresh — run /bedrock:sync to re-pull external sources, or /bedrock:sync --github / --people to surface recent activity and contributors.
Clean up drift — run /bedrock:compress to fix broken backlinks, merge duplicates, and consolidate fragmented concepts. Run /bedrock:healthcheck for a read-only report.
Manage multiple vaults — register several vaults with /bedrock:vaults; target a specific one with --vault <name>.

What you get in Obsidian

Every entity has YAML frontmatter (type, status, domain, sources), hierarchical tags (type/actor, status/active, domain/payments), and bidirectional wikilinks. The graph view becomes a navigable map of people, systems, teams, topics, and projects — updated automatically as you teach Bedrock new content.

Dependencies

Tool	Purpose	Required?
graphify	Semantic code extraction and knowledge-graph pipeline used by `/bedrock:learn` and `/bedrock:sync`	Yes
docling	Universal file → markdown converter used by `/bedrock:learn` to ingest DOCX, PPTX, XLSX, PDF, HTML, EPUB, images, and other non-markdown formats	Yes

Both graphify and docling are auto-installed by /bedrock:setup (and lazily by /bedrock:learn on first use if missing). You can also install them manually via pipx install graphify / pipx install docling.

Confluence and Google Docs ingestion are built into the plugin as internal skills (/bedrock:confluence-to-markdown, /bedrock:gdoc-to-markdown) invoked by /bedrock:learn and /bedrock:sync — no external installation required.

Configuration

Configuration is stored in .bedrock/config.json inside your vault. Run /bedrock:setup again at any time to reconfigure.

Error Reporting

The bedrock plugin auto-reports framework errors as GitHub issues on iurykrieger/claude-bedrock so maintainers learn about real-world failures.

What gets reported

Python tracebacks from skill scripts
Non-zero exit codes from skill bash commands
Known logical-failure phrases in Claude's text (small auditable regex catalog)

What never gets reported

Vault content (markdown bodies, frontmatter values)
Absolute filesystem paths (replaced with .../)
Vault entity names (people, teams, projects, etc.)
URLs from your vault (Confluence, Google Docs, internal repos)

How to opt out

Add "error_reporting": false to your vault's .bedrock/config.json:

{
  "error_reporting": false
}

Default is true. The hook silently skips reporting if gh is not installed or you're not authenticated, and logs the would-be report to ~/.claude-bedrock-cache/error-reporter.log.

Contributing

Contributions are welcome! Here's how to get started:

Fork the repository
Clone your fork and install the plugin locally:
```
claude --plugin-dir ./claude-bedrock
```
Create a branch for your feature or fix
Make your changes — skills live in skills/, entity definitions in entities/, templates in templates/
Test by running the plugin against a test vault
Open a PR against main

Project Structure

claude-bedrock/
├── .claude-plugin/    # Plugin manifest (plugin.json)
├── skills/            # Skill definitions (SKILL.md per skill)
│   ├── setup/
│   ├── query/
│   ├── teach/
│   ├── preserve/
│   ├── compress/
│   └── sync/
├── entities/          # Entity type definitions
├── templates/         # Frontmatter schema templates
├── docs/              # Documentation assets
├── CLAUDE.md          # AI agent instructions
└── README.md

License

MIT — Iury Krieger

File tree

210

iurykrieger/claude-bedrockView on GitHub ↗

.claude-plugin/
  marketplace.json
  plugin.json
.github/
  workflows/
    release.yml
.gitignore
.vibeflow/
  audits/
    adaptive-ask-orchestrator-audit.md
    ask-graph-index-audit.md
    bedrock-init-skill-audit.md
    code-graphify-bridge-part-1-audit.md
    code-graphify-bridge-part-2-audit.md
    code-graphify-bridge-part-3-audit.md
    compress-graph-broken-backlinks-audit.md
    compress-healthcheck-split-part-1-audit.md
    compress-healthcheck-split-part-2-audit.md
    concept-entity-audit.md
    configurable-git-strategy-part-1-audit.md
    configurable-git-strategy-part-2-audit.md
    fetcher-layered-fallback-audit.md
    fix-orphan-obsidian-files-audit.md
    genericize-plugin-part-1-audit.md
    genericize-plugin-part-2-audit.md
    genericize-plugin-part-3-audit.md
    graphify-pipeline-refactor-audit.md
    graphify-setup-autoinstall-audit.md
    improve-readme-audit.md
    internalize-content-fetchers-part-1-audit.md
    internalize-content-fetchers-part-2-audit.md
    landing-page-audit.md
    multiple-vaults-part-1-audit.md
    multiple-vaults-part-2-audit.md
    multiple-vaults-part-3-audit.md
    obsidian-default-config-audit.md
    query-graphify-engine-audit.md
    rename-knowledge-node-to-code-part-1-audit.md
    rename-knowledge-node-to-code-part-2-audit.md
    rename-query-to-ask-part-1-audit.md
    rename-query-to-ask-part-2-audit.md
    rename-teach-to-learn-audit.md
    site-redesign-part-1-audit.md
    site-redesign-part-2-audit.md
    site-redesign-part-3-audit.md
    teach-docling-integration-part-1-audit.md
    teach-docling-integration-part-2-audit.md
    teach-docling-integration-part-3-audit.md
    translate-plugin-to-en-us-audit.md
  conventions.md
  decisions.md
  index.md
  patterns/
    entity-definition.md
    skill-architecture.md
    skill-delegation.md
    template-structure.md
    vault-writing-rules.md
  prds/
    adaptive-ask-orchestrator.md
    ask-graph-index.md
    bedrock-init-skill.md
    code-graphify-bridge.md
    compress-graph-broken-backlinks.md
    compress-healthcheck-split.md
    concept-entity.md
    configurable-git-strategy.md
    fetcher-layered-fallback.md
    genericize-plugin.md
    graphify-pipeline-refactor.md
    graphify-setup-autoinstall.md
    internalize-content-fetchers.md
    landing-page.md
    multiple-vaults.md
    obsidian-default-config.md
    query-graphify-engine.md
    rename-knowledge-node-to-code.md
    rename-query-to-ask.md
    site-redesign-nextjs.md
    teach-docling-integration.md
  prompt-packs/
    fix-orphan-obsidian-files.md
    improve-readme.md
    readme-fixes.md
    rename-teach-to-learn.md
    translate-plugin-to-en-us.md
  specs/
    adaptive-ask-orchestrator.md
    ask-graph-index.md
    bedrock-init-skill.md
    code-graphify-bridge-part-1.md
    code-graphify-bridge-part-2.md
    code-graphify-bridge-part-3.md
    compress-graph-broken-backlinks.md
    compress-healthcheck-split-part-1.md
    compress-healthcheck-split-part-2.md
    concept-entity.md
    configurable-git-strategy-part-1.md
    configurable-git-strategy-part-2.md
    fetcher-layered-fallback.md
    genericize-glossary.md
    genericize-plugin-part-1.md
    genericize-plugin-part-2.md
    genericize-plugin-part-3.md
    graphify-pipeline-refactor.md
    graphify-setup-autoinstall.md
    internalize-content-fetchers-part-1.md
    internalize-content-fetchers-part-2.md
    landing-page.md
    multiple-vaults-part-1.md
    multiple-vaults-part-2.md
    multiple-vaults-part-3.md
    obsidian-default-config.md
    query-graphify-engine.md
    rename-knowledge-node-to-code-part-1.md
    rename-knowledge-node-to-code-part-2.md
    rename-query-to-ask-part-1.md
    rename-query-to-ask-part-2.md
    site-redesign-part-1.md
    site-redesign-part-2.md
    site-redesign-part-3.md
    teach-docling-integration-part-1.md
    teach-docling-integration-part-2.md
    teach-docling-integration-part-3.md
CLAUDE.md
docs/
  banner.png
entities/
  actor.md
  code.md
  concept.md
  discussion.md
  fleeting.md
  person.md
  project.md
  sources-field.md
  team.md
  topic.md
hooks/
  error_reporter.py
  hooks.json
  tests/
    __init__.py
    fixtures/
      transcript_bedrock_clean.jsonl
      transcript_bedrock_logical_error.jsonl
      transcript_bedrock_old_turn.jsonl
      transcript_bedrock_traceback.jsonl
      transcript_no_bedrock.jsonl
    test_config.py
    test_detection.py
    test_hashing.py
    test_issues.py
    test_main.py
    test_perf.py
    test_redaction.py
    test_transcript.py
index.html
LICENSE
README.md
site/
  .gitignore
  app/
    favicon.ico
    globals.css
    layout.tsx
    page.tsx
  components/
  components.json
    animate-in.tsx
    footer.tsx
    graph-canvas.tsx
    hero.tsx
    how-it-works.tsx
    installation.tsx
    navbar.tsx
    section-header.tsx
    skill-panel.tsx
    skills-showcase.tsx
    terminal-block.tsx
    ui/
      badge.tsx
      button.tsx
      tabs.tsx
    use-cases.tsx
    vault-demo.tsx
    vault-preview.tsx
    vault-sidebar.tsx
  data/
    skills.ts
    use-cases.ts
    vault-demo.ts
  eslint.config.mjs
  lib/
    utils.ts
  next.config.ts
  package-lock.json
  package.json
  postcss.config.mjs
  public/
    videos/
      ask.mp4
      compress.mp4
      graph-view.mp4
      preserve.mp4
      setup.mp4
      sync.mp4
      teach.mp4
      vault-navigation.mp4
  README.md
  tsconfig.json
skills/
  ask/
    SKILL.md
  compress/
    SKILL.md
  confluence-to-markdown/
    scripts/
      extract.js
    SKILL.md
  gdoc-to-markdown/
    scripts/
      extract.js
    SKILL.md
  healthcheck/
    SKILL.md
  learn/
    SKILL.md
  preserve/
    SKILL.md
  setup/
    SKILL.md
  sync/
    SKILL.md
  vaults/
    SKILL.md
templates/
  actors/
    _template_node.md
    _template.md
  concepts/
    _template.md
  discussions/
    _template.md
  fleeting/
    _template.md
  people/
    _template.md
  projects/
    _template.md
  teams/
    _template.md
  topics/
    _template.md

bedrock

Skills

Hooks

README

Features

Installation

Quick Start

Skills

Vault Structure

How It Works

First-time use

Day-to-day loops

What you get in Obsidian

Dependencies

Configuration

Error Reporting

Contributing

Project Structure

License

File tree