claude-obsidian is a local knowledge system that turns source material into linked, source-cited Markdown notes in an Obsidian vault for use with Claude Code and compatible agent hosts. People use it to capture research, retrieve evidence-grounded answers, maintain knowledge, and map connections while retaining ownership of their files. The catalogue entries provide workflows and extensions for operating this knowledge system.
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 skills add AgriciDaniel/claude-obsidian --skill defuddlegit clone --depth 1 https://github.com/AgriciDaniel/claude-obsidianWrote 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/skills/agricidaniel/claude-obsidian/defuddle)<a href="https://agentmods.dev/skills/agricidaniel/claude-obsidian/defuddle"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-obsidian/defuddle.svg" alt="Measured on agentmods" height="20"></a>- Socket warn
- Snyk warn
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 | $0.00057 | $0.00949 |
| Opus 5 | $0.00028 | $0.00475 |
| Sonnet 5 | $0.00011 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
defuddle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defuddle
Treat Defuddle as an optional external extractor, not an internal capability. Cleaning, raw capture, and wiki ingestion are separate operations.
Resolve the installed product root from this skill's own location, never from the selected vault or process working directory:
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"
If a separately installed kepano/obsidian-skills defuddle skill is
available, prefer it for current CLI flags. Retain the privacy, consent, and
transaction rules in this skill.
Safety contract
- Accept remote inputs only as HTTPS URLs.
- Reject credentials in URLs, fragments, private or local hosts, non-public IP addresses, control characters, and sensitive query parameters.
- Never interpolate a URL into a shell string. Pass it as one argv element.
- Treat redirects to a different host as denied until that host is explicitly approved.
- State that the URL and request metadata will leave the machine. Network access requires explicit consent in the current request or a separate confirmation.
- Do not install a cleaner, execute a placeholder runner, or silently switch to another network fetcher.
- Do not claim a fixed token reduction or extraction quality. Inspect the actual output.
Plan first
Create an inert URL plan. This validates the URL and executes no network call:
python3 "$CORE" capture external-plan url "HTTPS_URL"
Report the normalized host, network egress, redirect policy, optional external
dependency, and execute: false. Then inspect whether this package can find a
configured Defuddle executable:
python3 "$CORE" contracts --verify --capability defuddle --vault VAULT
An available state means no executable was found; stop with the inert plan.
A configured state means the executable was discovered, but this package has
no bundled behavioral verifier for it. Show that state and reason, identify the
resolved executable path, and require manual review of its provenance, version,
and exact argv before execution. Never relabel configured as verified.
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 · 105 lines · 57 tokens per session scan A 458b6a3fbd20
defuddle is a skill published in the GitHub repository AgriciDaniel/claude-obsidian (14,693 stars, last pushed 11d ago), licensed MIT. It adds 57 tokens to every session and 949 once invoked, about $0.0003 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 skills, from other repositories
dr-fanout
One command to fan a Deep Research prompt out to several external LLMs at once (ChatGPT / Gemini / Grok / others) through the operator's logged-in browser, then collect the reports, archive the originals, and synthesize a consensus. Trigger on "/dr-fanout", "fan out the DR", "distribute the research prompt". Automates…
fb-reply
Read who commented on the owner's recent Facebook posts and post PERSONALIZED replies through their real logged-in Chrome (live-tab, low-ban-risk), draft-first and rate-limit-guarded. Trigger on "/fb-reply", "reply to my facebook comments". Replying on your OWN posts is expected behavior; the guard enforces a daily…
canvas
AI-orchestrated visual production for Obsidian Canvas. Create presentations, flowcharts, mood boards, knowledge graphs, galleries, storyboards, timelines, dashboards, and more with intelligent layout and AI-generated content. Claude acts as Creative Director — dispatching sub-agents for image generation, SVG diagrams…
canvas-generate
AI-orchestrated full canvas generation. Given a description, detects the best archetype, generates content and visuals, instantiates a template, applies layout, and produces a complete canvas. The flagship command. Dispatches canvas-media and canvas-composer agents for parallel asset generation. Triggers on: canvas…
canvas-populate
Add content to existing Obsidian Canvas files. Supports all node types: images (with auto aspect ratio detection), text cards, PDFs, wiki notes, web links, Mermaid diagrams, SVGs, GIFs, AI-generated images via banana. Also adds zones (groups), edges between nodes, and imports recent banana images. Triggers on: canvas…
canvas-export
Export Obsidian Canvas files to PNG, SVG, or PDF formats. Uses the Advanced Canvas plugin's built-in export when Obsidian is running, or falls back to Playwright browser-based screenshot capture. Supports single canvas export, presentation slide-per-page PDF export, and batch export. Triggers on: canvas export, export…