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 mycelium-hq/ai-brain-starter --skill vault-systemgit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/vault-system)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/vault-system"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/vault-system/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/mycelium-hq/ai-brain-starter/vault-system"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/vault-system.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 | $0.00112 | $0.01287 |
| Opus 5 | $0.00056 | $0.00643 |
| Sonnet 5 | $0.00022 | $0.00257 |
| Haiku 4.5 | $0.00011 | $0.00129 |
Grade A, and why
vault-system 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 8d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vault system
Routes vault meta-maintenance — the vault AS a system (its markdown corpus, knowledge graph, drift monitors, rule extraction, substrate sync). Not the content; the substrate that makes the content queryable and auditable.
Distinct from:
- Querying the vault to answer a question (use the knowledge-graph query tools)
- Bringing external data INTO the vault (use the ingest skills)
- Daily journal + coaching + pattern detection (those operate inside the substrate)
This is the SUBSTRATE layer. It maintains what every other skill uses.
Step 1. Identify the maintenance moment
| Trigger | Skill / tool |
|---|---|
| Knowledge graph stale or never built for a corpus | graphify |
| Existing graph query (find concept / path / cluster) | your graph-query tool, or Obsidian graph view |
| Typed-file metadata extraction (books, meetings, people, articles, goals) | second-brain-mapping |
| Vault self-check (CLAUDE.md / Meta folder / skills / hooks / MCPs / journal index) | diagnose |
| Files edited many times in a short window (drift hotspot) | a drift-detection pass → a Drift Audit note |
| Recurring corruption pattern needs codification | codify it into a new rule file in your rules dir |
| Journals missing body / frontmatter context | backfill-journal-body-context |
| Vault types not yet set up (new vault or refresh) | setup-vault-types |
| Memory index getting long (truncation cliff) | consolidate-memory |
| Obsidian Bases / JSON Canvas / Markdown / CLI work | the matching obsidian:* skill |
If unclear → ask ONE question. Don't guess.
Step 2. Pre-flight
- Vault location: resolve the vault root (a
VAULT_PATH/VAULT_ROOTenv var, or the current directory). - Graph state: check whether a graph report exists and how fresh it is before answering graph questions.
- Drift state: check the latest drift-audit output.
- Rules state: list the rules directory.
- Memory state: check the memory index length (keep it under the truncation cliff).
- Git in a large vault: NEVER
git add -A/./ unscopedgit statuson a big vault — full-tree walks are slow and lock-contending. Use explicit paths.
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.
- 8d ago First seen · 97 lines · 112 tokens per session scan A 4dbd1894cfb1
vault-system is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (36 stars, last pushed yesterday), licensed MIT. It adds 112 tokens to every session and 1,287 once invoked, about $0.0006 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 2026-09-04.
Other skills, from other repositories
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".
resume-last
Collect the last human session, or a specific one by id, into a seed on the clipboard, so a new session continues where the old one broke off, including after a crash or on a machine where native resume does not work. Triggers: "/resume-last", "/resume", "continue the last session".
chatgpt-sync
Pull fresh ChatGPT conversations into an Obsidian vault on demand, the manual twin of the nightly job. Incremental and idempotent by conversation id: never clobbers enriched notes, never duplicates. Triggers: "/chatgpt-sync", "pull chatgpt", "sync chatgpt chats".
sessme
A command that lists recent multi-turn coding sessions and lets you choose one to restore in full.
obsidian-setup-consultant
Use this skill whenever the user wants to install, configure, migrate, design, or connect Obsidian as a second brain, knowledge base, cloud-synced vault, or AI/Hermes-readable memory. It is especially important when the user asks for an Obsidian setup prompt, vault architecture, folder structure, plugin…
memorb-born
Phase 0 Vault Initialization Skill: setup user identity, AI advisor persona, communication preferences, and core vault structure into CLAUDE.md. Triggered when vault setup is missing, user requests re-initialization, or running /memorb-born.