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 wiki-retrievegit 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/wiki-retrieve)<a href="https://agentmods.dev/skills/agricidaniel/claude-obsidian/wiki-retrieve"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-obsidian/wiki-retrieve/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/wiki-retrieve"><img src="https://agentmods.dev/badge/skills/agricidaniel/claude-obsidian/wiki-retrieve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- 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 | $0.00081 | $0.01661 |
| Opus 5.5 | $0.00032 | $0.00664 |
| Sonnet 5.5 | $0.00016 | $0.00332 |
| Haiku 4.5 | $0.00008 | $0.00166 |
Grade A, and why
wiki-retrieve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retrieve relevant passages
This extension derives search data from wiki/ into .vault-meta/. It never
changes canonical notes. Always pass the selected vault explicitly.
Resolve the installed product root from this skill's own location, not from the vault or current working directory:
PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
PREFIX="$PRODUCT_ROOT/scripts/contextual-prefix.py"
BM25="$PRODUCT_ROOT/scripts/bm25-index.py"
RETRIEVE="$PRODUCT_ROOT/scripts/retrieve.py"
RERANK="$PRODUCT_ROOT/scripts/rerank.py"
test -f "$PREFIX" && test -f "$BM25" && test -f "$RETRIEVE" && test -f "$RERANK"
Pipeline
contextual-prefix.pysplits pages on paragraph boundaries and stores the raw chunk plus a short page-level prefix.bm25-index.pybuilds a local, standard-library BM25 index over the contextualized text.retrieve.pyselects BM25 candidates, optionally reranks them, rejects invalid records, deduplicates by page, and returns paths and snippets.- The caller reads the returned pages and performs synthesis; retrieval output is not itself evidence.
Provision locally
Preview first, then build synthetic prefixes without network egress:
python3 "$PREFIX" --vault "$VAULT" --all --no-llm --peek
python3 "$PREFIX" --vault "$VAULT" --all --no-llm
python3 "$BM25" --vault "$VAULT" build
python3 "$RETRIEVE" --vault "$VAULT" "wiki" --top 1 --no-rerank --explain
Chunk and index files are disposable runtime state. Incremental prefixing skips records whose chunk hashes, page hashes and provider/model profile still match. Legacy records without that profile regenerate on an explicit build. A complete scan removes surplus records for deleted pages, and the prefixer invalidates the BM25 index before changing its chunk set so a mixed stale index is not served. Prefix and BM25 build operations share the vault-wide mutation lock with every other writer; a busy vault fails closed instead of publishing a partial index.
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.
- 2d ago Changed · +28 lines 654136eec357
- 1mo ago First seen · 119 lines · 81 tokens per session scan A 1e7735d493e9
wiki-retrieve is a skill published in the GitHub repository AgriciDaniel/claude-obsidian (15,757 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,661 once invoked, about $0.0003 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
screenpipe-api
Query the user's local and synced-device data via the screenpipe REST API at localhost:3030 — recordings, audio, UI, meetings, connected services, and memory. Use for screen activity, other-device or cross-device history, productivity, media export, connections, durable memory, or discovering and automating saved…
follower-onboard
Onboard a new machine as a receive-only follower on a multi-machine agent network: it reads the shared vault, canon, skills and memory, runs nothing heavy locally (no RAG, reindex or GPU), and never receives executable hooks from the hub. Checklist-driven, with a verify step at each stage. Triggers: "/follower-onboard…
brain-onboard
An onboarding workflow that helps another person create and use their own private knowledge store, sometimes called a second brain. It gathers their information with consent, saves it in their own workspace, and demonstrates a first useful result.
memory-tidy
Tidy an agent's always-loaded memory index (MEMORY.md) on macOS or Linux: trim long lines, move closed entries to an archive, fold domains into hub files, restore dropped pins and add pointers for orphan memory files. Use when the index is over budget or has orphans. Triggers: /memory-tidy, /mt, tidy memory.
claudeai-sync
Pull new and changed claude.ai web conversations into an Obsidian vault, extract artifacts as first-class notes, concept-link them, and refresh the RAG index and dashboard. Idempotent: curated notes are never overwritten. Triggers: "/claudeai-sync", "pull claude.ai", "grab new claude.ai chats".
chat-search
Search inside past agent sessions and continue the one that matters with a single command. Uses a separate episodic session index, so raw chat noise never pollutes the curated RAG. Triggers: "/chat-search", "which chat discussed X", "did we already research X", "search old chats".