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/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/skills/agricidaniel/claude-obsidian/defuddle"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-obsidian/defuddle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00061 | $0.01051 |
| Opus 5.5 | $0.00024 | $0.00420 |
| Sonnet 5.5 | $0.00012 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
defuddle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Defuddle
Treat Defuddle as an optional external extractor. This package supports inert URL plans and filesystem capture; it does not ship an enforcing network cleaner. Cleaning, raw capture, and wiki ingestion are separate operations.
Resolve the installed product root from this skill's own location, never from the selected vault or process working directory:
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"
Every ../wiki/references/ link in this file resolves the same way, relative
to this skill's own directory under $PRODUCT_ROOT, never relative to the
selected vault's wiki/ directory.
Upstream flags may be checked in a separately installed kepano/obsidian-skills
reference, but do not override this package's privacy and transaction boundary.
Inert URL plan
Accept HTTPS URLs only. Reject credentials, fragments, controls, sensitive query parameters, and non-public hosts or IP addresses. Never interpolate a URL into a shell string. Use one argv element when constructing a plan:
python3 "$CORE" capture external-plan url "HTTPS_URL"
python3 "$CORE" contracts --verify --capability defuddle --vault "$VAULT"
The plan executes no network request. Report the normalized host, required
network egress, redirect policy, optional dependency, and execute: false.
An available state means no executable was found. A configured state means
an executable was discovered without a bundled behavioral verifier. Identify
the manual executable and its reported reason; never run it merely because it
was found. Never relabel configured as verified.
Why execution stops here
The upstream CLI inspected at commit
556d74e8c8fd68c49912d4b11a4ae9ec04d7b2b5
(checked 2026-10-17) follows redirects and enables asynchronous extraction.
Even parsing a local HTML file can request additional resources or third-party
fallbacks. Inspecting argv or obtaining consent for the initial URL cannot
prove that every eventual destination remains approved.
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.
- yesterday Changed · -16 lines · +4 tokens per session 35958e30b352
- 1mo ago Changed · +4 lines f87f3ef75683
- 1mo ago First seen · 105 lines · 57 tokens per session scan A 458b6a3fbd20
defuddle is a skill published in the GitHub repository AgriciDaniel/claude-obsidian (15,732 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 1,051 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 skills, from other repositories
apply
A browser-based job application workflow for submitting applications through services such as Ashby, Greenhouse, Lever, and Hacker News. It uses prepared candidate information, answers, job links, and cover letters.
dr-fanout
Fan one deep-research prompt out to several external LLMs at once through a logged-in browser, then collect the reports, archive the originals and synthesize a consensus. Use at the final stage of a research protocol, instead of hand-pasting one prompt into N sites. Triggers: "/dr-fanout", "fan out the DR"…
cv-outreach
A daily workflow for carrying out scheduled outward-facing tasks, such as event registrations, messages to organisers, and public posts. It uses a browser identity carefully so actions are made from the intended account.
social-daily
A workflow for publishing prepared content to Facebook, X, Telegram, Threads, and Instagram. It uses a shared queue so posts for different platforms can be tracked together.
fb-reply
Read who commented on recent Facebook posts and publish personalized replies through the real logged-in Chrome tab, draft-first, with a daily cap and a minimum gap between replies. Triggers: "/fb-reply", "reply to my facebook comments".
fb-likes
A Facebook engagement workflow for carrying out recurring likes on your own posts, comments, replies, and selected contacts' content.