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 larsboes/Axon --skill obsidiangit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/obsidian)<a href="https://agentmods.dev/skills/larsboes/axon/obsidian"><img src="https://agentmods.dev/badge/skills/larsboes/axon/obsidian.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 | $0.00136 | $0.01650 |
| Opus 5 | $0.00068 | $0.00825 |
| Sonnet 5 | $0.00027 | $0.00330 |
| Haiku 4.5 | $0.00014 | $0.00165 |
Grade A, and why
obsidian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obsidian
The vault is an Obsidian Life OS, not a code repo, and it is the one place knowledge is allowed to be durable. Anything worth keeping ends up here as a typed note — not in a session transcript, not in a scratch file, not in a second system beside the vault.
1 · Resolve and gate (always first, never hardcode)
VAULT=$(scripts/vault root) # from the overlay's config/knowledge.toml
scripts/vault contract # fails loudly if the contract is missing
Read $VAULT/Projects/Soma/Vault-Contract.md before creating, moving, or retyping any note.
It owns placement, the no-doubling law, naming, and frontmatter typing. If it is missing, stop and
say so — do not improvise structure. $VAULT/AGENTS.md is the vault-side pointer to the same file.
Three rules from it that gate every single write, restated because they are what goes wrong:
- Type at birth. No note without
type:+maturity: seedling+summary:+categories:. - One owner per kind of statement. A concept is Knowledge, a proper-noun instance is Atlas, a
consumed work is
Atlas/Media(ideas graduate to a Knowledge concept), what-happened isAtlas/Events+ Journal, a pattern isAtlas/Reflections, a decision is the Project. Assert once; thread everywhere with[[links]]. - Update the owner in place. A new note must earn its folder; a new folder needs 3+ notes.
2 · Read before you act
Almost everything already has a home. Grep the vault and open the owning note before answering a planning or "update my X" request — the job is to find where it lives, not to invent a new place. A note with no inbound or outbound link is a leak.
3 · Pick the reference
| Task | Read |
|---|---|
| Wikilinks, embeds, callouts, properties | references/markdown.md |
.base views, filters, formulas |
references/bases.md |
.canvas files |
references/canvas.md |
| Obsidian CLI (notes, search, properties, plugin dev) | references/cli.md, then obsidian help — authoritative |
| Ingest a source · synthesize across notes · lint the wiki | references/wiki.md |
What ships with it
6 files 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.
- 7d ago First seen · 111 lines · 136 tokens per session scan A 1a244a749c60
obsidian is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed today), licensed MIT. It adds 136 tokens to every session and 1,650 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
reflect
Use Recall Reflect to review AI coding workflow history as a conversation-first timeline and discuss observed patterns before changing behavior. Trigger when the user asks to reflect on a project, review AI coding workflow, inspect workflow friction, discuss repeated corrections, review handoffs, or explore possible…
any-mcp
Use when an agent needs to read, search, create, edit, organize, upload, or chat with Anytype through the bounded any-mcp server. Covers safe tool selection, exact identifier chaining, optional toolsets, common PKM workflows, and the narrow anyr fallbacks for chat subscriptions and rich chat blocks.
recap
Summarize the last N agent sessions for the current project, grouped by date, with highlight observations per session. Use when the user asks "recap", "what have we been doing", "today", "this week", or wants a rollup of recent work.
alcove-hub
Use when working from the Alcove hub workspace or routing personal knowledge, pins, projects, prompts, tasks, mounts, connectors, or managed KB operations.
alcove-workspace
Use inside a lightweight Alcove business workspace for scoped personal knowledge, pins, tasks, ideas, and prompt reuse.
knowledge-coach
Organize knowledge, detect recurring friction, plan review, and provide evidence-based encouragement without making unsupported psychological claims.