obsidian-wiki is a framework that helps AI agents build and maintain an interconnected knowledge base from text-based material in an Obsidian vault. It is for people who want their agents to remember discoveries, connect related information, and answer questions with wiki-link citations. Catalogue add-ons provide the agent skills, instructions, agents, and configuration used to create and maintain these wikis.
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 Ar9av/obsidian-wiki --skill wiki-narrategit clone --depth 1 https://github.com/Ar9av/obsidian-wikiWrote 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/ar9av/obsidian-wiki/wiki-narrate)<a href="https://agentmods.dev/skills/ar9av/obsidian-wiki/wiki-narrate"><img src="https://agentmods.dev/badge/skills/ar9av/obsidian-wiki/wiki-narrate/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/ar9av/obsidian-wiki/wiki-narrate"><img src="https://agentmods.dev/badge/skills/ar9av/obsidian-wiki/wiki-narrate.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 | $0.00050 | $0.01526 |
| Opus 5 | $0.00025 | $0.00763 |
| Sonnet 5 | $0.00010 | $0.00305 |
| Haiku 4.5 | $0.00005 | $0.00153 |
Grade A, and why
wiki-narrate 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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Narrate — Cited Narrative Readouts
Use this skill only for a topic-based Markdown readout. Do not add tag or page-list selection, prior-query input, voice aliases, HTML, PDF, slides, renderer handoffs, or new compiled knowledge pages.
Command Contract
/wiki-narrate <topic> [--voice briefing|plain-language|lecturer] [--save]
- Require a non-empty
<topic>. - The default voice is
briefing. - Voice names are canonical and case-sensitive. Unsupported values must return an
error listing
briefing,plain-language, andlecturerwithout searching or writing. --saveis the only persistence switch.- For a missing topic, malformed option, or unsupported voice, return a short usage
or validation error and do not search, write, append a log event, or change
hot.md.
Retrieval
Writing profile: Before drafting or rewriting natural-language Markdown, read and apply the Writing Profile Resolution section in llm-wiki/SKILL.md. Framework schema, provenance, safety, and operation-specific requirements take precedence.
WRITING.md preferences apply only to newly drafted or rewritten natural-language Markdown; preserve source content and structured records.
- Resolve configuration with the Config Resolution Protocol, including an inline
@namevault override, then read the target vault'sAGENTS.mdwhen it exists. LoadOBSIDIAN_LINK_FORMATbefore drafting citations. - Read
hot.mdandindex.mdfirst. Select candidates by frontmatter and summary before reading bodies. - When configured, use QMD before
rg; if QMD is absent, unconfigured, or fails, continue with the index andrgpath. Treat QMD output as candidate guidance, not evidence: establish each claim from the allowed vault page itself. - Honor filtered-mode phrases such as "public only", "user-facing", "no internal
content", "as a user would see it", and "exclude internal". Skip pages tagged
visibility/internalorvisibility/piiin that mode: never read, cite, or expose them. - Exclude
_readouts/,_raw/,_archives/,_meta/,index.md,log.md,hot.md, and_insights.mdfrom candidates. - Read matching sections before full pages, and read full pages only when a factual claim cannot otherwise be established. Preserve relevant lifecycle and freshness annotations; do not upgrade a page's trust.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 121 lines · 50 tokens per session scan A 980e40497e08
wiki-narrate is a skill published in the GitHub repository Ar9av/obsidian-wiki (3,381 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 1,526 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
knowledge-base-management
A lifecycle system for managing an Obsidian knowledge base, which is a folder of linked notes. It organizes raw material, AI-maintained wiki pages, and generated views into separate layers.
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
llm-wiki
Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.