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 agentmods add commands/michael-ovo/obsidian-knowledge-agent/setupgit clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agentWhat 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 | $0.00019 | $0.00672 |
| Opus 5 | $0.00010 | $0.00336 |
| Sonnet 5 | $0.00004 | $0.00134 |
| Haiku 4.5 | $0.00002 | $0.00067 |
Grade A, and why
setup 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up the current folder as an Obsidian Knowledge Agent vault. Detect first, then do the least surprising thing. Always idempotent — never clobber anything that exists.
Step 0 — Detect the folder and tell me which mode you're in:
- Already a vault —
.agents/learned/exists → RESUME (don't re-scaffold). - An existing Obsidian vault — has notes / an
.obsidian/folder, but no.agents/learned/→ ADOPT (fit what's there, fill only the gaps). - Empty / new folder — no notes, no vault structure → SCAFFOLD (build a starter).
Then run the matching mode:
RESUME — it's already set up
Don't re-create anything. Report status in a couple of lines — the branches, how many
items are in Inbox/, the last journal.md entry — and route me to work:
"Inbox has 3 items — want me to :ingest? Or tell me what to capture." Stop there.
ADOPT — an existing vault (the adaptive path)
- Read, don't impose. Map the existing top-level folders, naming style, and the frontmatter on a few notes. Treat that as the vault's conventions — do not add new branch folders or rename anything.
- Fill only the gaps. Create
.agents/learned/(journal.md,conventions.md,examples.md, askills/folder) only if missing; addInbox/and aDashboard.mdmap-of-content that links the existing branches. Never overwrite existing files. - Seed conventions for review. Write what you detected (naming, frontmatter, folder
shape) into
.agents/learned/conventions.mdas a proposed starting point, and show me the diff before committing it. - Commit the additions, then point me at
/obsidian-knowledge:help.
SCAFFOLD — an empty folder
- Branches. Create top-level branch folders — from
$ARGUMENTSif given, otherwise propose a small default (a sharedReferences/plus one or two domains) and confirm with me before creating. Give each branch an_index.md. - Learning state. Create
.agents/learned/withjournal.md,conventions.md,examples.md, and askills/folder — seed empty starters. - Inbox + dashboard. Create
Inbox/and aDashboard.mdmap-of-content that links the branches and explains the workflow in a line or two. - Commit the scaffold, then point me at
/obsidian-knowledge:helpand suggest dropping a first source intoInbox/.
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 First seen · 48 lines · 19 tokens per session scan A e7c581dfbb31
setup is a command published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (207 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 672 once invoked, about $0.0001 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 commands, from other repositories
design
Early-stage design exploration — settle the shape of a feature/recipe/system before scoping its implementation. Re-entrant; agent-judged writes.
scope
Project-level scoping — refine a single living vault note for a project, with mandatory unknowns tracking. Re-entrant; agent-judged writes.
decompose
Feature/story breakdown — consume a ready-for-decompose scope doc and produce a task graph in the issue tracker. Re-entrant; tracker-as-canonical with vault breadcrumb.
implement
Feature implementation in a repo — ticket → plan gate → develop-to-plan → draft-PR review loop (human gate) → squash-clean finalize. Thin recipe over six overridable primitives; dossier-mcp the only hard dependency.
research
Conversation-shaped research loop — vault grounding + web research + agent-judged capture (no pre-write sign-off).
dossier
Force load of Dossier vault profile (and inbox check) before processing the rest of the user's request.