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/ingestgit clone --depth 1 https://github.com/Michael-OvO/obsidian-knowledge-agentWrote 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/commands/michael-ovo/obsidian-knowledge-agent/ingest)<a href="https://agentmods.dev/commands/michael-ovo/obsidian-knowledge-agent/ingest"><img src="https://agentmods.dev/badge/commands/michael-ovo/obsidian-knowledge-agent/ingest.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.00374 |
| Opus 5 | $0.00010 | $0.00187 |
| Sonnet 5 | $0.00004 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
ingest 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 6d 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.
What it actually says
Handle whatever I point you at — or everything in Inbox/ if I don't say.
If this folder isn't a vault yet (no .agents/ and no notes), don't force a build —
say so and offer /obsidian-knowledge:setup first, then come back to this.
- Recall. If this vault has
.agents/learned/, readconventions.mdandexamples.mdand scan.agents/learned/skills/for a matching playbook. Look at how this vault is already organized and plan to fit in, not impose. - Pick the altitude. Match the effort to the material — a single note (Capture),
a few notes plus a light index (Small collection), or the full scaffold with a
concept-graph canvas (Full build). Default to the lightest that fits; when unsure,
go lighter and offer to go deeper. See "Choose the altitude" in
.agents/ingestion-workflow.md. (For an obvious one-note save, just use/obsidian-knowledge:capture.) - Do the work at that altitude, following the
obsidian-knowledgeskill and the vault's.agents/*.mdif present (otherwise the skill's bundledreferences/). - Reflect. Append a journal entry and propose any durable convention / example / playbook updates for review. Commit per the approval policy; surface rule-change diffs before committing them.
$ARGUMENTS
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.
- 6d ago First seen · 27 lines · 21 tokens per session scan A c66b675780a7
ingest is a command published in the GitHub repository Michael-OvO/obsidian-knowledge-agent (206 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 374 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
install
Guided setup for a new Cowork workspace. Interviews you (about 5 minutes) and generates a full, pre-configured cowork-os workspace (folders, copy, project instructions, and recurring routines).
process-inbox
Process the inbox. Read everything the user dropped in (notes, links, a deck, a messy folder) and route each fact to the most specific workspace file, separating facts from assumptions and open questions, without inventing anything.
plan
Create implementation plan with risk assessment.
caveman-compress
Compress a markdown/text file into caveman format to save tokens.
fire-todos
Capture, list, and manage todos during work sessions.
wikimate-link
관련 노트끼리 [[링크]]로 연결(자동 링크, 노트당 최대 5개) 또는 같은 주제 노트를 목차(MOC)로 묶기.